© 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. 110926
    Prev
    Next
    INDEX
    Explanations

    punchy

    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
    iriya
    0.40
    谥
    0.39
    icus
    0.38
     வழி
    0.38
    ኩ
    0.38
    ötzlich
    0.38
     poł
    0.38
    遌
    0.37
    ijske
    0.37
     Karam
    0.37
    POSITIVE LOGITS
     punch
    0.59
    Punch
    0.58
    punch
    0.50
     punched
    0.50
     Punch
    0.50
     punches
    0.45
     punching
    0.44
    礴
    0.40
    扎
    0.39
    down
    0.36
    Activations Density 0.006%

    No Known Activations