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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 200278
    Prev
    Next
    INDEX
    Explanations

    danger and harm

    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
    iflower
    0.44
     Mash
    0.42
     Air
    0.41
    ,
    0.41
    可谓
    0.41
    典型
    0.40
    iances
    0.39
     Hints
    0.39
    oload
    0.39
    到的
    0.39
    POSITIVE LOGITS
    ේ
    0.48
    𝗴
    0.46
    OPLE
    0.45
    ANGLE
    0.45
     građ
    0.45
     ángulo
    0.44
     dưới
    0.44
    drawLine
    0.43
    ני
    0.43
    င်
    0.42
    Activations Density 0.008%

    No Known Activations