© 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. 72605
    Prev
    Next
    INDEX
    Explanations

    ISBNs and specifications

    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
     of
    -1.71
    :
    -1.52
     baden
    -1.30
     a
    -1.28
     Division
    -1.14
     distinctive
    -1.13
     predominantly
    -1.11
     goddamn
    -1.10
     cartaz
    -1.09
    際には
    -1.09
    POSITIVE LOGITS
    Spesifikasi
    1.42
    INGRED
    1.42
    Karakter
    1.38
    INGREDIENT
    1.32
     garner
    1.31
    Kelebihan
    1.31
    かで
    1.26
    Kontra
    1.26
    Fär
    1.25
     другу
    1.24
    Activations Density 0.000%

    No Known Activations