© 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. 113022
    Prev
    Next
    INDEX
    Explanations

    south, CNN, https, More, Can, like

    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
    //
    -2.78
    鎳
    -2.73
    谖
    -2.66
    雳
    -2.59
    身后的
    -2.55
    身边的
    -2.53
    iscono
    -2.41
     capitalize
    -2.41
    这只
    -2.38
     tekno
    -2.36
    POSITIVE LOGITS
    咴
    3.33
    pecabe
    3.25
    拶
    3.02
     wherein
    2.91
    </td>
    2.77
    寕
    2.67
    鹛
    2.67
     albeit
    2.61
    pulseira
    2.52
    荩
    2.50
    Activations Density 0.025%

    No Known Activations