© 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. 67525
    Prev
    Next
    INDEX
    Explanations

    people or places

    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
    嚶
    -2.64
    但我
    -2.64
    </td>
    -2.41
     —
    -2.34
    癩
    -2.30
    瓒
    -2.28
    窨
    -2.28
    书房
    -2.22
    婓
    -2.20
     Kommunikations
    -2.19
    POSITIVE LOGITS
     The
    3.00
     THERE
    2.98
    
    2.80
    there
    2.75
     unſ
    2.73
    4
    2.73
    including
    2.70
     VERY
    2.69
    翆
    2.64
    𨭆
    2.56
    Activations Density 0.012%

    No Known Activations