© 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. 59425
    Prev
    Next
    INDEX
    Explanations

    #include, Ceiling Tile

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

    The neuron strongly activates on enumeration markers and numeric or code‐style tokens—e.g. list indices (1, A), version numbers or ports, preprocessor numbers, and similar numeric or enumerator strings.

    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
     lou
    -0.85
    Stateful
    -0.71
    监管
    -0.70
    sista
    -0.69
    Domains
    -0.69
    roud
    -0.69
    Teles
    -0.69
    ギー
    -0.68
     Tequila
    -0.68
    ця
    -0.67
    POSITIVE LOGITS
     auroit
    0.67
    ďte
    0.63
    เขียน
    0.61
    deca
    0.61
     Jacobi
    0.60
     enfrenta
    0.60
    gradient
    0.60
     krijgt
    0.60
    readLine
    0.59
    objet
    0.59
    Activations Density 0.044%

    No Known Activations