© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 113491
    Prev
    Next
    INDEX
    Explanations

    normalizing harmful content

    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
    ك
    0.83
    IAL
    0.80
              
    0.71
     fino
    0.70
    s
    0.70
    g
    0.65
    im
    0.64
    де
    0.64
     not
    0.64
         
    0.63
    POSITIVE LOGITS
     정상
    0.85
    erweise
    0.85
     عادی
    0.84
    正常
    0.80
     normales
    0.77
     असामान्य
    0.75
     норма
    0.73
    異常
    0.73
    正常的
    0.73
     অস্বাভাবিক
    0.71
    Activations Density 0.036%

    No Known Activations