© 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. 67104
    Prev
    Next
    INDEX
    Explanations

    leads to

    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
    6
    -2.08
    8
    -2.08
    '
    -2.05
    "
    -1.98
     faſt
    -1.89
    5
    -1.84
     siste
    -1.82
    }
    -1.76
    9
    -1.73
    //
    -1.72
    POSITIVE LOGITS
    他对
    2.14
     Surely
    2.11
     you
    1.98
     tohoto
    1.92
    蘩
    1.89
     obrá
    1.87
    atella
    1.87
     Temos
    1.87
    さてさて
    1.83
     jeweiligen
    1.81
    Activations Density 0.024%

    No Known Activations