© 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. 22-GEMMASCOPE-RES-131K
    7. 26282
    Prev
    Next
    INDEX
    Explanations

    headings or labels like "Post", "Woman", "By", "Q"

    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
     mostrarse
    -1.00
     czarne
    -0.93
    礴
    -0.91
    katu
    -0.91
     rękaw
    -0.90
     usarlo
    -0.90
     descubrió
    -0.90
     not
    -0.90
     Think
    -0.89
     colchón
    -0.89
    POSITIVE LOGITS
    number
    0.89
     accepte
    0.89
     continuer
    0.89
    previous
    0.88
     tambien
    0.88
     смотре
    0.87
    total
    0.85
    🔙
    0.85
     Recomend
    0.85
    に
    0.84
    Activations Density 0.003%

    No Known Activations