© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13902
    Prev
    Next
    INDEX
    Explanations

    CGRectMake and point coordinates

    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
     reasons
    -1.23
     still
    -1.22
     reason
    -1.21
    いなかった
    -1.11
     etc
    -1.11
    همچنین
    -1.10
     포함
    -1.06
     selezione
    -1.05
     Its
    -1.04
     also
    -1.03
    POSITIVE LOGITS
     gitar
    1.21
     berge
    1.13
     gånger
    1.12
     kado
    1.09
     makro
    1.09
    kinda
    1.09
    🧵
    1.08
    婓
    1.05
     ríos
    1.04
     paru
    1.03
    Activations Density 0.005%

    No Known Activations