© 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. 44391
    Prev
    Next
    INDEX
    Explanations

    rules, specific detail, vary significantly

    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
    鱻
    0.48
    ဆင့်
    0.48
    ურთი
    0.48
    riente
    0.45
     Enhancement
    0.45
    rion
    0.45
    clouds
    0.44
    Θ
    0.43
    <bos>
    0.43
     பிள்ளை
    0.43
    POSITIVE LOGITS
     penalized
    0.52
     relieved
    0.51
     prioritized
    0.51
     ограничен
    0.51
    тана
    0.50
     taken
    0.50
     oficiais
    0.48
     depressed
    0.47
     голов
    0.47
     backed
    0.46
    Activations Density 0.000%

    No Known Activations