© 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. 130463
    Prev
    Next
    INDEX
    Explanations

    in front of

    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
     jenem
    -2.13
    .
    -2.08
    6
    -1.99
     jenen
    -1.95
     keinem
    -1.94
     welchem
    -1.94
    2
    -1.92
    8
    -1.90
     verschied
    -1.82
     Dijo
    -1.82
    POSITIVE LOGITS
    举例
    1.77
     sabias
    1.76
    ൮
    1.69
     also
    1.67
     ktorí
    1.63
    柺
    1.63
     основном
    1.63
    )...
    1.56
     nuoc
    1.56
     a
    1.55
    Activations Density 0.005%

    No Known Activations