© 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. 72647
    Prev
    Next
    INDEX
    Explanations

    Q: questions and Guerilla terms

    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
     tidligere
    -1.22
     apresentado
    -1.08
     tatuagem
    -1.08
     you
    -1.05
     easily
    -1.05
    Sighs
    -1.02
    了啊
    -1.02
    Fallout
    -1.02
     برگزاری
    -1.02
     mesma
    -1.01
    POSITIVE LOGITS
    Indeed
    1.33
     Chbosky
    1.24
    ҝ
    1.23
    が
    1.20
    </em>
    1.18
    ensões
    1.17
    ने
    1.15
    ън
    1.13
    nappropriate
    1.12
     hogy
    1.11
    Activations Density 0.000%

    No Known Activations