Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 6492
    Prev
    Next
    INDEX
    Explanations

    block of code

    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
    ला
    1.99
    ش
    1.94
     비롯
    1.93
    ্যা
    1.85
    ري
    1.79
    то
    1.76
    軀
    1.74
    з
    1.72
    ли
    1.67
    ರ
    1.66
    POSITIVE LOGITS
    认为是
    2.03
    busters
    1.98
    下旬
    1.94
    ﺼ
    1.93
    speople
    1.84
    chains
    1.82
    uları
    1.82
    THING
    1.80
    রুখ
    1.80
     anthrac
    1.77
    Activations Density 0.043%

    No Known Activations