© 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. 10-GEMMASCOPE-RES-131K
    7. 8986
    Prev
    Next
    INDEX
    Explanations

    here or now leading to context

    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
     and
    -1.54
     Schriftsteller
    -1.53
     Because
    -1.52
    ivät
    -1.47
    怎么能
    -1.45
    wachen
    -1.45
     spooky
    -1.36
     Politiker
    -1.28
     بالح
    -1.28
    汕
    -1.26
    POSITIVE LOGITS
     firmar
    1.55
    骉
    1.53
     retirer
    1.45
    แล้ว
    1.38
     verbund
    1.32
    „
    1.31
     traductions
    1.30
    発送
    1.28
     integran
    1.24
     leſs
    1.24
    Activations Density 0.017%

    No Known Activations