© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 33385
    Prev
    Next
    INDEX
    Explanations

    code block keywords/identifiers

    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
    撂
    -1.00
    鮰
    -0.97
    ฀
    -0.97
     recente
    -0.97
    nové
    -0.97
     rechte
    -0.94
     Puntos
    -0.93
    ∷
    -0.93
    たまた
    -0.92
     Maintenant
    -0.91
    POSITIVE LOGITS
     or
    1.30
     with
    1.20
     if
    1.12
     in
    1.11
     extraordinarily
    1.08
    Some
    1.05
     after
    1.03
     without
    1.03
     moderately
    1.02
    After
    0.99
    Activations Density 0.004%

    No Known Activations