© 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. 22-GEMMASCOPE-RES-131K
    7. 129429
    Prev
    Next
    INDEX
    Explanations

    foreign and domestic news

    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_22/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
     السياس
    -1.40
     usar
    -1.38
    <strong>
    -1.34
     vuelve
    -1.34
     zaś
    -1.27
    tispiece
    -1.27
     usando
    -1.25
    拦
    -1.25
     buscar
    -1.21
     buscando
    -1.21
    POSITIVE LOGITS
    ★☆
    1.45
     because
    1.44
    スポンサーリンク
    1.41
    Hvem
    1.33
     diing
    1.32
    おはよう
    1.30
    いかがでしたか
    1.30
    ⣛
    1.29
    inafter
    1.28
     jaja
    1.28
    Activations Density 0.009%

    No Known Activations