© 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. 40130
    Prev
    Next
    INDEX
    Explanations

    Rwanda and Kigali

    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
     if
    -1.97
    </i>
    -1.58
     our
    -1.55
    al
    -1.53
     or
    -1.50
    h
    -1.41
    {
    -1.41
     this
    -1.38
    ’，
    -1.38
     "
    -1.38
    POSITIVE LOGITS
     especí
    1.63
    untuk
    1.61
    schöne
    1.54
    雳
    1.45
     finnas
    1.45
     användas
    1.44
    isées
    1.38
    ኙ
    1.37
    InjectAttribute
    1.35
    𓐍
    1.35
    Activations Density 0.009%

    No Known Activations