© 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. 53874
    Prev
    Next
    INDEX
    Explanations

    import model definitions

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

    This neuron selectively fires on programming‐style syntax tokens—e.g. import statements, punctuation like parentheses and dots, numeric literals, and other code symbols.

    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
    ここに
    -0.75
     Endocrinol
    -0.75
    零售
    -0.74
    wać
    -0.74
     svårt
    -0.73
     دیگران
    -0.73
     literario
    -0.73
     Ärzte
    -0.72
    Comics
    -0.72
     Universität
    -0.72
    POSITIVE LOGITS
    tka
    1.02
    felf
    0.94
     }}\
    0.85
     tivi
    0.84
    oughby
    0.84
    réhen
    0.81
    تل
    0.81
    ndag
    0.81
     Phần
    0.77
     Became
    0.77
    Activations Density 0.003%

    No Known Activations