© 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-16K
    7. 3415
    Prev
    Next
    INDEX
    Explanations

    stylesheet link

    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_16k_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
    ä
    1.33
    ana
    1.17
    ه
    1.10
    ao
    1.09
    ia
    1.05
    iu
    1.05
    aceous
    1.05
    ,
    1.05
    mselves
    1.05
    atum
    1.04
    POSITIVE LOGITS
    DD
    1.20
    znam
    1.20
     aparelho
    1.13
     иных
    1.12
    ለያዩ
    1.10
    ｼ
    1.10
    ル
    1.09
     অন্যান্য
    1.09
    AZIONE
    1.05
    ૩
    1.05
    Activations Density 0.034%

    No Known Activations