© 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. 65867
    Prev
    Next
    INDEX
    Explanations

    subsequent/successive timing

    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
    有助
    -0.96
     доро
    -0.94
     (
    -0.94
     by
    -0.91
    /
    -0.89
    -
    -0.89
     as
    -0.88
     đang
    -0.85
    AUTH
    -0.85
     are
    -0.84
    POSITIVE LOGITS
    ristorante
    1.17
     subsequent
    1.16
     successive
    1.13
    時には
    1.12
     '/';
    1.07
     successivamente
    1.07
    好評
    1.05
    ungkap
    1.05
     abbiamo
    1.04
     Posteriormente
    1.03
    Activations Density 0.043%

    No Known Activations