© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27354
    Prev
    Next
    INDEX
    Explanations

    starts descriptions

    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_22/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
     Obwohl
    -1.23
    に行ってきました
    -1.17
     Gleichzeitig
    -1.16
     NSCoder
    -1.15
     Möglich
    -1.13
    vud
    -1.12
    orant
    -1.11
    がありますが
    -1.09
     Einige
    -1.08
     recientes
    -1.07
    POSITIVE LOGITS
     your
    1.94
     you
    1.93
     also
    1.50
    是你
    1.17
     is
    1.15
     TUESDAY
    1.10
     italia
    1.09
    你就
    1.09
     nostre
    1.06
     Wikiped
    1.06
    Activations Density 0.045%

    No Known Activations