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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76094
    Prev
    Next
    INDEX
    Explanations

    in vitro

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

    code-related content, especially in programming files and markup language documents.

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

    The neuron fires strongly on tokens containing digits (i.e. numeric sequences or numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     SND
    -0.71
     Nef
    -0.68
    CRE
    -0.65
    EventLoop
    -0.62
     CRE
    -0.62
    jne
    -0.62
    gimento
    -0.60
     Pind
    -0.60
     &(
    -0.60
    钩
    -0.60
    POSITIVE LOGITS
    RAL
    0.67
    转移
    0.66
    μά
    0.66
    BASS
    0.65
    TRANSFER
    0.65
     hamlet
    0.65
    Eds
    0.63
    INTERRUPT
    0.63
    Interrupt
    0.63
     ifrån
    0.62
    Activations Density 0.089%

    No Known Activations