© 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. 10-GEMMASCOPE-RES-131K
    7. 99230
    Prev
    Next
    INDEX
    Explanations

    technical terms followed by related devices

    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
     to
    -2.02
     décé
    -1.79
    ፨
    -1.75
     permitirá
    -1.70
     dará
    -1.63
     récla
    -1.52
    Ār
    -1.51
     indicada
    -1.48
    硃
    -1.48
     aceit
    -1.47
    POSITIVE LOGITS
     only
    1.75
     with
    1.62
    $
    1.43
     about
    1.41
     remainder
    1.39
     is
    1.35
     cannot
    1.31
     hecta
    1.30
     cerimonia
    1.29
    2
    1.29
    Activations Density 0.355%

    No Known Activations