© 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. 3582
    Prev
    Next
    INDEX
    Explanations

    vision and environment

    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
     যাবতীয়
    0.81
    ១
    0.79
    ní
    0.79
    譎
    0.79
    парт
    0.75
     ይመ
    0.75
    បុ
    0.75
    ៦
    0.73
    psz
    0.73
     മറ്റ്
    0.72
    POSITIVE LOGITS
    ulfanyl
    0.77
     conquest
    0.75
    ezi
    0.73
    }$,
    0.73
     sola
    0.71
    }$-
    0.70
    வுடன்
    0.70
    umā
    0.70
    ችል
    0.68
    ulosa
    0.68
    Activations Density 0.000%

    No Known Activations