© 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. 290
    Prev
    Next
    INDEX
    Explanations

    rude behavior

    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
    s
    2.05
    ut
    1.76
    ள்
    1.59
    ם
    1.54
    ration
    1.53
    //$
    1.53
    ri
    1.52
    ारी
    1.51
    ın
    1.45
    한
    1.45
    POSITIVE LOGITS
    issionais
    1.88
     созда
    1.84
     zosta
    1.72
     transformada
    1.66
    czenia
    1.65
     teis
    1.62
     causado
    1.61
     всеки
    1.58
    তে
    1.55
     οπο
    1.55
    Activations Density 0.002%

    No Known Activations