© 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. 1466
    Prev
    Next
    INDEX
    Explanations

    people's actions and preferences

    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
    ل
    2.16
    ير
    1.61
    ність
    1.52
    لین
    1.52
    س
    1.52
    った
    1.51
    이기
    1.51
    で
    1.51
    야
    1.47
    нням
    1.45
    POSITIVE LOGITS
    ം
    1.98
    ం
    1.89
    ంట్
    1.79
    ाई
    1.77
    ért
    1.75
    tr
    1.73
     phonons
    1.71
    و
    1.68
    ون
    1.61
    い
    1.59
    Activations Density 0.039%

    No Known Activations