© 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. 44590
    Prev
    Next
    INDEX
    Explanations

    notice and abstract

    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
     =
    -2.69
    辚
    -2.63
    d
    -2.28
    鼷
    -2.27
    RE
    -2.25
    嫘
    -2.23
    푆
    -2.17
     eller
    -2.06
    AL
    -2.03
    providedIn
    -2.02
    POSITIVE LOGITS
     Hinblick
    3.14
     Another
    2.95
     There
    2.53
     Gegensatz
    2.45
     we
    2.44
     Vordergrund
    2.39
     Zeitraum
    2.39
     vorigen
    2.36
     originalen
    2.30
     Suitable
    2.22
    Activations Density 0.007%

    No Known Activations