© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 4208
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ی
    2.39
    metik
    2.31
    iamo
    2.22
    要知道
    2.11
    ことにより
    2.05
     trasport
    2.02
     darse
    1.99
    strate
    1.95
     sepen
    1.92
    ary
    1.91
    POSITIVE LOGITS
    ות
    1.94
     glimpses
    1.85
    टर
    1.84
     pathologist
    1.78
    u
    1.68
     👀
    1.63
     plight
    1.61
    к
    1.61
    тор
    1.60
    ే
    1.60
    Activations Density 0.099%

    No Known Activations