© 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. 68677
    Prev
    Next
    INDEX
    Explanations

    official organizations and titles

    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
     اخیر
    -1.31
    retten
    -1.30
    toja
    -1.27
     continu
    -1.18
     you
    -1.17
     muy
    -1.11
     послед
    -1.08
     we
    -1.08
    <u>
    -1.07
     perci
    -1.06
    POSITIVE LOGITS
     cucchiai
    1.15
     nélk
    1.09
    französ
    1.09
    ־ה
    1.09
     RISERV
    1.09
    --(
    1.05
    篳
    1.05
    炷
    1.05
     &,
    1.04
    ‾
    1.04
    Activations Density 0.010%

    No Known Activations