© 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. 34-GEMMASCOPE-RES-131K
    7. 32515
    Prev
    Next
    INDEX
    Explanations

    Environment.Exit

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

    The neuron fires on tokens that look like programming‐language code elements—identifiers, keywords, operators, and similar code syntax.

    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
     jw
    -0.79
    FEN
    -0.71
    scrollTop
    -0.70
    tiu
    -0.69
     分享
    -0.68
     comparator
    -0.68
     vios
    -0.68
    TID
    -0.68
    FQ
    -0.68
     Chou
    -0.68
    POSITIVE LOGITS
     guten
    0.74
     elementos
    0.70
    VM
    0.70
     нако
    0.68
    vcpu
    0.68
     leyes
    0.66
    liche
    0.65
     objetivo
    0.63
    arski
    0.63
     VM
    0.63
    Activations Density 0.052%

    No Known Activations