© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 9482
    Prev
    Next
    INDEX
    Explanations

    voluntary, spontaneous, unsolicited

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    Impact
    -0.93
    tigem
    -0.90
     –
    -0.88
     Cia
    -0.88
     honoring
    -0.83
     permit
    -0.81
     impact
    -0.81
    ^^;
    -0.81
     има
    -0.80
     reserving
    -0.80
    POSITIVE LOGITS
     voluntarily
    1.57
     voluntary
    1.49
    oluntary
    1.22
     Voluntary
    1.18
     self
    1.16
     espont
    1.14
     unsolicited
    1.11
     spontaneous
    1.10
     spontaneously
    1.02
     volontaire
    1.02
    Activations Density 0.056%

    No Known Activations