© 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. 22-GEMMASCOPE-RES-131K
    7. 15691
    Prev
    Next
    INDEX
    Explanations

    measurement of

    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
     хотят
    -1.19
     déclaration
    -1.11
    ｻ
    -1.08
     statunit
    -1.08
     in
    -1.07
    맘
    -1.03
     Լ
    -1.03
    จริงๆ
    -1.02
     missione
    -1.02
    充滿
    -0.98
    POSITIVE LOGITS
     of
    3.42
     a
    1.44
    了一些
    1.32
     og
    1.24
    了不少
    1.22
     Ã
    1.18
    谖
    1.16
    colgante
    1.16
    жность
    1.15
     an
    1.14
    Activations Density 0.165%

    No Known Activations