© 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. 67741
    Prev
    Next
    INDEX
    Explanations

    state of charge

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

    This neuron fires on identifiers containing underscores (e.g. variable or parameter names with “_” in them).

    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
     accepte
    -1.90
    甞
    -1.77
     Octobre
    -1.73
     voer
    -1.73
    耷
    -1.71
     ActionBar
    -1.69
    攥
    -1.66
     herbes
    -1.63
     perles
    -1.60
     appartements
    -1.59
    POSITIVE LOGITS
     we
    2.56
     more
    2.08
     of
    2.00
     Many
    1.91
     when
    1.91
     some
    1.88
     our
    1.88
     When
    1.87
     a
    1.80
     Various
    1.75
    Activations Density 0.007%

    No Known Activations