© 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. 84578
    Prev
    Next
    INDEX
    Explanations

    value assignment or definition

    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
    硨
    -3.03
    t
    -2.98
    ?”
    -2.59
    梘
    -2.58
    不会
    -2.50
    ”-
    -2.48
    antaranya
    -2.48
    岿
    -2.47
    熘
    -2.34
    ”.
    -2.33
    POSITIVE LOGITS
     
    2.77
    .'"
    2.63
    とも
    2.50
    celotti
    2.47
     Begleitung
    2.38
     جديدة
    2.33
    艽
    2.33
    ⚋
    2.31
     It
    2.30
    ᪥
    2.27
    Activations Density 0.059%

    No Known Activations