© 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. 93002
    Prev
    Next
    INDEX
    Explanations

    HTTP request methods

    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
     asiática
    -1.02
     kolorze
    -0.98
     minne
    -0.97
     kupa
    -0.97
     formie
    -0.96
     our
    -0.96
     sors
    -0.95
    ⿰
    -0.94
    子は
    -0.94
    läng
    -0.93
    POSITIVE LOGITS
     достиг
    1.05
    Kemudian
    1.03
    čného
    0.94
     Mbappe
    0.92
     ۱۷
    0.91
    onov
    0.91
     qualcosa
    0.90
    eaky
    0.90
    zzar
    0.87
    🛥
    0.87
    Activations Density 0.000%

    No Known Activations