© 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. 66507
    Prev
    Next
    INDEX
    Explanations

    public class declarations

    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
     those
    -1.24
     kartą
    -0.98
     have
    -0.97
    Дереккөздер
    -0.93
     pueden
    -0.88
    (
    
    -0.88
     some
    -0.86
    ℕ
    -0.86
     Verordnung
    -0.86
    řejmě
    -0.85
    POSITIVE LOGITS
     złota
    1.09
     coûts
    1.02
     comportements
    1.01
    ську
    0.97
     един
    0.93
     décisions
    0.93
    を選択します
    0.92
    brought
    0.92
    notated
    0.89
     trajets
    0.88
    Activations Density 0.045%

    No Known Activations