© 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-262K
    7. 131482
    Prev
    Next
    INDEX
    Explanations

    kernel driver

    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_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
     температуре
    0.42
     nivel
    0.41
    🟥
    0.40
    ombo
    0.39
    चलित
    0.39
     pung
    0.39
    getLevel
    0.39
    рів
    0.39
    Level
    0.38
    ropower
    0.38
    POSITIVE LOGITS
     normalizing
    0.47
     لیګ
    0.38
     Normalized
    0.38
    Normalization
    0.38
    驃
    0.37
     eigenvalue
    0.37
    涣
    0.37
    ভান
    0.37
    Cage
    0.36
    熵
    0.36
    Activations Density 0.000%

    No Known Activations