© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28182
    Prev
    Next
    INDEX
    Explanations

    change events

    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
    oprecipitation
    -0.93
    ASIS
    -0.93
     prevé
    -0.91
    small
    -0.90
    similar
    -0.89
    zzo
    -0.88
     cadeaux
    -0.86
    apo
    -0.85
     entsprechen
    -0.85
    Believe
    -0.85
    POSITIVE LOGITS
     changes
    1.55
     changed
    1.16
     changing
    1.13
     change
    1.13
     or
    0.94
     terminée
    0.93
     increased
    0.91
     ALWAYS
    0.90
    ૬
    0.88
     determining
    0.87
    Activations Density 0.006%

    No Known Activations