© 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. 21554
    Prev
    Next
    INDEX
    Explanations

    determine the or whether

    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
     civiles
    -1.98
     таких
    -1.95
    떳
    -1.94
    
    -1.91
    }
    -1.91
    𖣘
    -1.86
    蹰
    -1.79
     queste
    -1.75
     celana
    -1.72
     【
    -1.69
    POSITIVE LOGITS
     why
    2.03
     使っ
    1.80
     whether
    1.78
     there
    1.78
     and
    1.76
     especially
    1.64
     because
    1.63
    o
    1.63
     if
    1.63
    <em>
    1.59
    Activations Density 0.070%

    No Known Activations