© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 7169
    Prev
    Next
    INDEX
    Explanations

    surreal abstract art and shifting visuals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
     patriots
    0.89
    优惠
    0.89
     Redskins
    0.88
     креди
    0.88
    しっかり
    0.87
     bequem
    0.86
     galerinha
    0.86
     👍
    0.85
     prudent
    0.85
    培训
    0.85
    POSITIVE LOGITS
     surreal
    1.83
     sculptural
    1.61
     psychedelic
    1.55
     Surreal
    1.49
     sculptures
    1.43
     enigmatic
    1.38
     sculpture
    1.37
     fractal
    1.37
     kaleidoscopic
    1.36
     meditative
    1.35
    Activations Density 0.870%

    No Known Activations