© 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. 40-GEMMASCOPE-2-RES-65K
    7. 3653
    Prev
    Next
    INDEX
    Explanations

    comparisons and thresholds

    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_40_width_65k_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
    зка
    0.41
    デザ
    0.40
    蹩
    0.38
    ченко
    0.38
    Ꮠ
    0.37
    优化
    0.36
     확장
    0.35
    라
    0.35
     শব
    0.35
    实际
    0.35
    POSITIVE LOGITS
     threshold
    1.79
    threshold
    1.63
     thresholds
    1.54
     Threshold
    1.45
    阈
    1.41
    Threshold
    1.37
    閾
    1.20
    THRESHOLD
    1.18
    thresh
    1.01
     thresh
    1.00
    Activations Density 0.330%

    No Known Activations