© 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. 10-GEMMASCOPE-RES-131K
    7. 90890
    Prev
    Next
    INDEX
    Explanations

    passage or verses

    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
    {
    -1.82
     The
    -1.68
    chenen
    -1.53
     kapag
    -1.43
    то
    -1.43
    }
    -1.43
    枼
    -1.37
     complètes
    -1.36
     超
    -1.35
     serre
    -1.30
    POSITIVE LOGITS
     about
    2.06
     the
    1.72
     Begleitung
    1.69
    鐔
    1.59
     erwäh
    1.57
     these
    1.56
     Atual
    1.55
    "}}>
    1.55
    昔から
    1.52
     that
    1.52
    Activations Density 0.021%

    No Known Activations