© 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. 34-GEMMASCOPE-RES-131K
    7. 58213
    Prev
    Next
    INDEX
    Explanations

    places and proper names

    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_34/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
     Stomp
    -0.73
    新华
    -0.73
     dunes
    -0.73
     décadas
    -0.71
    %"
    -0.71
    عمال
    -0.70
    })));
    -0.70
     evidently
    -0.70
     decades
    -0.69
    |}\
    -0.69
    POSITIVE LOGITS
     Canadian
    0.82
     Canada
    0.78
    <0xC9>
    0.73
    lause
    0.73
     houten
    0.72
     Cana
    0.71
     propriétaires
    0.71
     Wird
    0.71
    thenburg
    0.69
     échanti
    0.69
    Activations Density 0.038%

    No Known Activations