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. 1185
    Prev
    Next
    INDEX
    Explanations

    names, places, or concepts

    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
    㠻
    0.85
     diurnal
    0.85
    ከተ
    0.83
    }.}
    0.82
     весьма
    0.80
    閆
    0.80
     medall
    0.79
    Დ
    0.79
     lysis
    0.78
     comércio
    0.78
    POSITIVE LOGITS
     *
    0.93
     \*
    0.75
    ©
    0.74
     °
    0.73
     ®
    0.72
    めん
    0.72
    man
    0.71
    ed
    0.71
     Ê
    0.67
     Gods
    0.67
    Activations Density 0.000%

    No Known Activations