© 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. 65961
    Prev
    Next
    INDEX
    Explanations

    script/com

    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
    εβ
    -1.05
    dotte
    -1.02
     of
    -1.01
     disfraces
    -1.00
    OGRAPH
    -1.00
    ‘
    -0.98
    डी
    -0.96
    اری
    -0.95
     världen
    -0.95
     bricolaje
    -0.95
    POSITIVE LOGITS
    Encontra
    1.33
    Kilde
    1.27
    Détails
    1.25
     rimanere
    1.16
    Especific
    1.13
    Hilsen
    1.12
    Solu
    1.11
    Dettagli
    1.10
    Onze
    1.10
    Välkommen
    1.09
    Activations Density 0.035%

    No Known Activations