© 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. 10-GEMMASCOPE-RES-131K
    4. 59573
    Prev
    Next
    INDEX
    Explanations

    for now

    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_10/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
    taler
    -1.61
     tragé
    -1.48
     również
    -1.48
    createDate
    -1.41
    もありました
    -1.41
    onShow
    -1.38
     from
    -1.36
     for
    -1.35
    atoren
    -1.34
     Desenvolvimento
    -1.34
    POSITIVE LOGITS
     «
    1.70
    and
    1.63
    ay
    1.57
    ot
    1.51
    or
    1.49
    don
    1.48
    go
    1.45
    no
    1.45
    to
    1.41
    ^{}
    1.40
    Activations Density 0.011%

    No Known Activations