© 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. 40-GEMMASCOPE-2-RES-262K
    7. 16343
    Prev
    Next
    INDEX
    Explanations

    body

    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
     तकनीक
    0.40
    личи
    0.39
    engagement
    0.38
    hairstyle
    0.38
    どうぞ
    0.37
    钽
    0.36
     Blink
    0.36
    ப்பட்டன
    0.35
    duel
    0.35
     उपस्थिति
    0.35
    POSITIVE LOGITS
     body
    0.80
     Body
    0.76
    Body
    0.75
    body
    0.68
    몸
    0.61
    BODY
    0.60
     BODY
    0.60
     몸
    0.59
     bodies
    0.57
     ದೇಹ
    0.57
    Activations Density 0.001%

    No Known Activations