© 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. 33067
    Prev
    Next
    INDEX
    Explanations

    months and years

    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
     dédié
    -1.10
    १
    -1.05
     tbsp
    -1.04
     vacía
    -1.02
     temporaire
    -1.01
     nedan
    -0.97
    韌
    -0.97
    катери
    -0.95
     Вален
    -0.94
    なのでしょう
    -0.94
    POSITIVE LOGITS
     of
    1.20
     it
    1.04
     again
    1.03
     Hinsicht
    0.96
    妄想
    0.92
     instead
    0.91
    もあった
    0.89
     each
    0.89
    скі
    0.87
    ？』
    0.87
    Activations Density 0.020%

    No Known Activations