© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113616
    Prev
    Next
    INDEX
    Explanations

    chemical abbreviations

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

    DNA nucleotide sequences or chemical compounds related to genetic or biochemical research.

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

    The neuron fires on short uppercase nucleotide k-mers (e.g. AGT, ACT, AGC), i.e. DNA oligonucleotide sequence tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     and
    -1.90
    hörige
    -1.70
    ྅
    -1.55
    几个月
    -1.52
    是怎么
    -1.52
    Hashtag
    -1.51
    りましたが
    -1.50
    hadapi
    -1.49
     ensured
    -1.48
     белая
    -1.45
    POSITIVE LOGITS
    the
    2.28
     $
    2.02
     This
    1.84
    篥
    1.77
    to
    1.75
    "));
    1.71
    饧
    1.69
    This
    1.66
    咴
    1.63
    licópter
    1.55
    Activations Density 0.001%

    No Known Activations