© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67429
    Prev
    Next
    INDEX
    Explanations

    android ui layout

    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
    になったら
    -1.16
     habló
    -1.13
    Both
    -1.09
     además
    -1.09
     first
    -1.07
    Why
    -1.04
    Each
    -1.03
    Under
    -1.02
    Whether
    -1.01
     betreffenden
    -1.00
    POSITIVE LOGITS
    .");
    1.17
     gustos
    1.09
    があり
    1.07
     redus
    1.06
     instante
    1.04
     contextes
    1.03
    ");
    1.01
    ంట
    0.98
     poils
    0.98
     cardin
    0.98
    Activations Density 0.001%

    No Known Activations