© 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. 106922
    Prev
    Next
    INDEX
    Explanations

    continue plans

    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
    慫
    -1.26
     quelquefois
    -1.16
     péché
    -1.11
    无奈
    -1.09
    quels
    -1.09
    挣扎
    -1.09
    犹豫
    -1.07
    otho
    -1.06
     sortant
    -1.06
     siè
    -1.04
    POSITIVE LOGITS
     weiterhin
    1.50
     continues
    1.45
     visit
    1.41
     confront
    1.39
    再次
    1.35
     finally
    1.28
     continue
    1.28
     plans
    1.27
     plan
    1.23
     learn
    1.23
    Activations Density 0.022%

    No Known Activations