© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69480
    Prev
    Next
    INDEX
    Explanations

    declare global partial `class`

    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
     Répondre
    -1.70
     Veuillez
    -1.53
     ausreich
    -1.41
     Aucune
    -1.38
    _
    -1.38
    ことはありません
    -1.35
     intérêts
    -1.34
     mengatakan
    -1.34
     Lorsque
    -1.32
     Prayers
    -1.32
    POSITIVE LOGITS
     in
    1.98
     and
    1.64
     on
    1.59
    引言
    1.38
    formación
    1.34
     仔
    1.34
    otropy
    1.30
    NING
    1.29
    execSQL
    1.28
    primitive
    1.27
    Activations Density 0.045%

    No Known Activations