© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15343
    Prev
    Next
    INDEX
    Explanations

    code comments and installation keywords

    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
     of
    -2.14
    ।
    -1.48
    }
    -1.48
     их
    -1.46
     его
    -1.41
    ,'
    -1.39
     she
    -1.38
    ®,
    -1.37
     permet
    -1.36
     через
    -1.34
    POSITIVE LOGITS
    ayant
    1.38
    祼
    1.37
     résoudre
    1.36
    took
    1.35
     nung
    1.34
    猡
    1.34
    ziak
    1.32
    lllllllll
    1.31
     asmen
    1.30
    ressing
    1.30
    Activations Density 0.090%

    No Known Activations