© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 43086
    Prev
    Next
    INDEX
    Explanations

    addressing groups informally

    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
    the
    1.13
    ']:
    1.13
    ที่คุณ
    1.09
     sorti
    1.08
     stades
    1.08
    0
    1.08
     unscathed
    1.07
     alami
    1.05
    ting
    1.05
    น
    1.04
    POSITIVE LOGITS
    á
    1.19
    〝
    1.12
    го
    1.09
    )
    1.03
    añas
    1.02
    v
    1.02
    ką
    0.98
    ūr
    0.98
    vät
    0.97
    jí
    0.97
    Activations Density 0.001%

    No Known Activations