© 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. 102738
    Prev
    Next
    INDEX
    Explanations

    code syntax elements

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

    opening parentheses in code, especially for function calls and parameter lists.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron picks out floating-point numeric literals (numbers with decimal points).

    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
    锖
    -2.27
    ⛛
    -2.03
    ☫
    -1.95
    憷
    -1.95
    ſſen
    -1.91
     皇族
    -1.87
     Médico
    -1.85
    ⸫
    -1.84
    𐬹
    -1.82
    桄
    -1.81
    POSITIVE LOGITS
    Some
    2.44
    Despite
    2.34
    During
    2.31
    There
    2.30
    At
    2.30
    Every
    2.30
    These
    2.28
    While
    2.27
    With
    2.23
    After
    2.22
    Activations Density 0.010%

    No Known Activations