© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4394
    Prev
    Next
    INDEX
    Explanations

    thresholds and numerical comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hazırl
    0.36
     görev
    0.34
    ങ്ങളും
    0.34
    猜测
    0.33
    снов
    0.33
    壶
    0.33
    Premi
    0.33
    Ticker
    0.32
     Павел
    0.32
     సంగ
    0.32
    POSITIVE LOGITS
     threshold
    1.02
     thresholds
    0.95
    threshold
    0.92
     Threshold
    0.80
     >=
    0.79
     ≤
    0.75
    Threshold
    0.75
     ≥
    0.74
     (>
    0.71
     $(<
    0.70
    Activations Density 0.262%

    No Known Activations