© 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. 10-GEMMASCOPE-RES-131K
    7. 14704
    Prev
    Next
    INDEX
    Explanations

    geographical regions and nations

    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_10/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
    ⸒
    -1.49
    åter
    -1.43
     about
    -1.41
     maría
    -1.41
     nostre
    -1.41
     Nuestros
    -1.41
     Ráp
    -1.40
     mußte
    -1.39
     campes
    -1.36
    —“
    -1.34
    POSITIVE LOGITS
     of
    1.74
    要知道
    1.59
     whom
    1.44
    ENCIÓN
    1.39
    providedIn
    1.35
     različ
    1.34
     Weisheit
    1.32
    『
    1.31
     necesitan
    1.30
     I
    1.27
    Activations Density 0.017%

    No Known Activations