© 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. 10-GEMMASCOPE-RES-131K
    7. 129618
    Prev
    Next
    INDEX
    Explanations

    index variable or database index

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

    This neuron fires on programming identifiers—tokens like variable names (e.g. “idx”), API names (e.g. “nibBundleOrNil”), and file‐extension tokens (e.g. “.cxx”).

    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
    }
    -2.94
     vollständ
    -2.89
    )-
    -2.86
    廕
    -2.83
     as
    -2.83
    轫
    -2.81
    ↵
    -2.75
     includes
    -2.69
     from
    -2.66
    }$
    -2.66
    POSITIVE LOGITS
    ꪹ
    2.98
    ſu
    2.89
    たまに
    2.78
    鵙
    2.77
    在我
    2.72
    樒
    2.72
    姌
    2.69
    翃
    2.63
     OTHER
    2.61
     dieß
    2.61
    Activations Density 0.000%

    No Known Activations