© 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. 26679
    Prev
    Next
    INDEX
    Explanations

    effort to/of/with

    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
     ſch
    -2.70
    鱚
    -2.56
     bolsillos
    -2.53
     tirantes
    -2.45
     cordón
    -2.42
     acabados
    -2.42
     suche
    -2.41
    大人気
    -2.38
     малень
    -2.34
    鱨
    -2.31
    POSITIVE LOGITS
     to
    3.30
    n
    2.64
    s
    2.56
    .
    2.56
    $
    2.45
    ter
    2.31
    al
    2.31
    an
    2.23
     That
    2.20
    us
    2.14
    Activations Density 0.012%

    No Known Activations