© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 53464
    Prev
    Next
    INDEX
    Explanations

    violation and support

    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
    𝐯
    0.45
    റും
    0.45
    Якщо
    0.43
     সংখ্য
    0.43
     paździer
    0.43
    效应
    0.43
    überküloz
    0.43
    Ⲃ
    0.42
     privileges
    0.42
    第一題
    0.42
    POSITIVE LOGITS
    radian
    0.50
    condition
    0.49
    char
    0.48
    h
    0.44
    hout
    0.43
    t
    0.43
    gent
    0.43
    cross
    0.43
     I
    0.42
    ch
    0.42
    Activations Density 0.000%

    No Known Activations