© 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. 39781
    Prev
    Next
    INDEX
    Explanations

    click on something

    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
    In
    -1.91
    <em>
    -1.66
    他の
    -1.60
     autre
    -1.58
    <strong>
    -1.58
    
    -1.46
     you
    -1.43
    いただ
    -1.39
    </blockquote>
    -1.38
    ement
    -1.37
    POSITIVE LOGITS
    を行いました
    1.69
    釙
    1.64
     влия
    1.61
     verheir
    1.56
    釭
    1.55
    噐
    1.53
    cartera
    1.48
    勦
    1.46
    をしました
    1.45
    andowski
    1.44
    Activations Density 0.049%

    No Known Activations