© 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. 14820
    Prev
    Next
    INDEX
    Explanations

    key term descriptors

    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
     during
    -1.56
    IonicModule
    -1.38
    gabri
    -1.32
    islamic
    -1.29
     to
    -1.25
    berserk
    -1.22
     mellom
    -1.20
    julie
    -1.18
    fallout
    -1.17
    lapping
    -1.16
    POSITIVE LOGITS
     máte
    1.58
    了一会儿
    1.54
     doté
    1.47
     приготовить
    1.41
     Setelah
    1.41
     realmente
    1.34
    riften
    1.32
    ون
    1.31
     récomp
    1.29
     &
    1.26
    Activations Density 0.037%

    No Known Activations