© 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. 1363
    Prev
    Next
    INDEX
    Explanations

    any kind

    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
     tahap
    0.97
    आर
    0.96
    mannschaft
    0.95
    ٹ
    0.92
    fungsi
    0.87
    нг
    0.84
    Ox
    0.83
    टेन
    0.83
     jantung
    0.82
     acides
    0.82
    POSITIVE LOGITS
    t
    1.27
    お
    1.01
    st
    0.98
    𝓸
    0.98
    d
    0.98
     необходимые
    0.97
     специальные
    0.96
    র
    0.95
    ра
    0.95
     специальных
    0.91
    Activations Density 0.000%

    No Known Activations