© 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. 65099
    Prev
    Next
    INDEX
    Explanations

    annual events

    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
     restricciones
    -1.38
     modificaciones
    -1.10
     limitaciones
    -1.09
     первых
    -1.05
    AFA
    -1.03
    six
    -1.02
    急に
    -1.02
     disponer
    -1.02
     Olympic
    -1.00
     arcilla
    -1.00
    POSITIVE LOGITS
     anual
    1.50
     which
    1.38
     murah
    1.28
    !」
    1.19
     pistola
    1.18
     annuel
    1.17
     of
    1.14
    rrrrrrrr
    1.14
    rennen
    1.12
    ‼
    1.12
    Activations Density 0.061%

    No Known Activations