© 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. 128098
    Prev
    Next
    INDEX
    Explanations

    XML/pickle serialization

    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
     their
    -1.34
     its
    -1.16
     less
    -1.13
     Without
    -1.12
     not
    -1.11
     both
    -1.10
     quite
    -1.05
     substantially
    -1.04
     or
    -1.04
     more
    -1.03
    POSITIVE LOGITS
    vikle
    1.05
     exercer
    0.99
    があり
    0.98
    larg
    0.93
     effec
    0.91
     principes
    0.90
     RURAL
    0.89
     τις
    0.88
    dotto
    0.88
     visse
    0.88
    Activations Density 0.000%

    No Known Activations