© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71443
    Prev
    Next
    INDEX
    Explanations

    sequence identity and homology

    np_acts-logits-general · gemini-2.5-flash-lite

    sequences showing percentage identity or similarity between proteins or DNA sequences.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects numeric measurements and identifiers in scientific text—especially numbers denoting sequence lengths, counts, and percentage identities.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     设置
    -1.55
     effects
    -1.49
     effect
    -1.31
    viembre
    -1.30
     children
    -1.26
    を使って
    -1.24
     mechanism
    -1.23
     获取
    -1.20
     mechanisms
    -1.20
    ILog
    -1.20
    POSITIVE LOGITS
     عاشقانه
    1.39
     confidently
    1.39
     باشیم
    1.20
    angerschaft
    1.16
     navnet
    1.16
    ạch
    1.14
    хождения
    1.13
     onCreateView
    1.12
     confident
    1.10
    ennung
    1.10
    Activations Density 0.144%

    No Known Activations