© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 54933
    Prev
    Next
    INDEX
    Explanations

    consecutive wins or streaks

    np_acts-logits-general · gemini-2.5-flash-lite

    consecutive occurrences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    还有
    0.46
    何度
    0.46
    Throughout
    0.46
    ในปี
    0.45
    还
    0.45
    ুরা
    0.43
    보
    0.43
    िप
    0.42
    Approximately
    0.42
    IK
    0.42
    POSITIVE LOGITS
     consecutive
    0.93
    連續
    0.90
    連続
    0.84
     consecut
    0.83
     연속
    0.82
     consecutivos
    0.82
     consecutively
    0.79
    连续
    0.75
     Consecutive
    0.74
     sequential
    0.70
    Activations Density 0.045%

    No Known Activations