© 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. 129003
    Prev
    Next
    INDEX
    Explanations

    code structure and punctuation

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

    The neuron fires on the “.” (and similar punctuation) that follows an identifier in member‐access, namespacing, or type‐qualification expressions.

    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
     and
    -2.11
     to
    -1.77
    </em>
    -1.58
    </h4>
    -1.51
    躂
    -1.45
    hObject
    -1.40
     who
    -1.39
    ⿴
    -1.39
    sohn
    -1.37
     tion
    -1.36
    POSITIVE LOGITS
    >
    1.55
     “
    1.55
     сьогодні
    1.53
     bekan
    1.53
     них
    1.53
    The
    1.52
     clásico
    1.47
     riguard
    1.47
    While
    1.44
    ・・
    1.44
    Activations Density 0.001%

    No Known Activations