© 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. 100163
    Prev
    Next
    INDEX
    Explanations

    hundred and units of measure

    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
    -3.17
    3
    -3.09
    恥ず
    -3.06
    2
    -3.05
    5
    -2.97
    6
    -2.92
     一
    -2.86
    たまに
    -2.84
     нескольких
    -2.73
     overarching
    -2.72
    POSITIVE LOGITS
    </em>
    3.09
    遄
    2.98
    ୯
    2.70
    嬗
    2.61
    镭
    2.61
     }(\
    2.61
    沇
    2.56
    ']),
    2.55
    趵
    2.53
    zione
    2.50
    Activations Density 0.005%

    No Known Activations