© 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. 53-GEMMASCOPE-2-RES-262K
    7. 14704
    Prev
    Next
    INDEX
    Explanations

    crazy, insane, wild

    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_53_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
     eloquence
    0.43
     esth
    0.40
     Oe
    0.39
     excellent
    0.39
     eloquent
    0.38
     Rost
    0.38
     dignit
    0.38
    尴
    0.38
     leit
    0.37
     Greenberg
    0.37
    POSITIVE LOGITS
     crazy
    2.98
    crazy
    2.69
    Crazy
    2.63
     Crazy
    2.59
     insane
    2.58
     craziness
    2.45
     insanity
    2.28
    疯狂
    2.20
    瘋
    2.09
     craz
    2.02
    Activations Density 0.059%

    No Known Activations