© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 31522
    Prev
    Next
    INDEX
    Explanations

    chess openings and moves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
     formada
    0.98
     formed
    0.89
     p
    0.89
    v
    0.88
    ется
    0.87
     👇
    0.86
     received
    0.84
     s
    0.84
     but
    0.82
    敤
    0.82
    POSITIVE LOGITS
     өз
    0.98
    accompl
    0.94
    ूपी
    0.94
    эк
    0.93
    asic
    0.92
    edf
    0.92
    équipement
    0.88
    анг
    0.88
    icycl
    0.88
    ों
    0.87
    Activations Density 0.007%

    No Known Activations