© 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. 31609
    Prev
    Next
    INDEX
    Explanations

    expert advice and teams

    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
    ي
    1.48
    عي
    1.37
    ا
    1.33
    い
    1.33
     difíc
    1.21
    Чтобы
    1.20
    ió
    1.20
    יא
    1.18
    𝚘
    1.18
    ana
    1.17
    POSITIVE LOGITS
    पणे
    1.19
     observations
    0.97
    िक
    0.97
    ed
    0.96
     microwave
    0.95
    辑
    0.95
    ↵↵
    0.94
     consolidated
    0.94
     skilful
    0.94
    俩
    0.94
    Activations Density 0.000%

    No Known Activations