© 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. 128259
    Prev
    Next
    INDEX
    Explanations

    AV followed by technical terms

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

    The neuron consistently activates on code identifiers beginning with “AV,” i.e. AVFoundation–style class or API names.

    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
    which
    -3.28
    yarakat
    -2.47
    鏵
    -2.36
    茈
    -2.36
     melap
    -2.33
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -2.25
    鋮
    -2.25
     誕生
    -2.23
    oretical
    -2.20
     começaram
    -2.20
    POSITIVE LOGITS
     was
    3.14
     '
    2.72
    --
    2.55
     You
    2.48
     proclaim
    2.38
    ࿚
    2.33
     soothe
    2.33
     意思
    2.28
    _
    2.23
     ugly
    2.20
    Activations Density 0.009%

    No Known Activations