© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 14665
    Prev
    Next
    INDEX
    Explanations

    quoted strings in code

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

    The neuron fires on string‐delimiting quote characters (and their backslash escape sequences).

    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
     maillot
    -1.37
     autobus
    -1.36
    
    -1.35
     ͡
    -1.31
    縵
    -1.30
    をつけ
    -1.30
    agulation
    -1.29
    吅
    -1.29
    dimento
    -1.27
    纐
    -1.27
    POSITIVE LOGITS
     are
    1.91
     would
    1.73
     on
    1.63
    ’
    1.51
     or
    1.47
     “
    1.46
     should
    1.44
    );
    1.44
    ).
    1.38
    ):
    1.28
    Activations Density 0.126%

    No Known Activations