© 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. 34080
    Prev
    Next
    INDEX
    Explanations

    rates or ratios

    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
     металла
    -1.11
    で
    -1.05
     Leinwand
    -1.05
    

    -1.03
    に
    -1.03
     nachdem
    -1.02
    上
    -1.01
    …
    -1.00
    ↵↵
    -0.98
    と
    -0.98
    POSITIVE LOGITS
    providedIn
    1.27
     biela
    1.20
     each
    1.19
     вересня
    1.16
    此人
    1.14
    cazione
    1.13
    神话
    1.13
     farba
    1.12
     isolé
    1.12
     familières
    1.11
    Activations Density 0.013%

    No Known Activations