© 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. 982
    Prev
    Next
    INDEX
    Explanations

    greetings and farewells

    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
    на
    1.68
    न
    1.52
    ن
    1.37
    นอก
    1.24
    ни
    1.23
    นิด
    1.23
    نا
    1.20
    ח
    1.19
    น
    1.18
    นาง
    1.17
    POSITIVE LOGITS
    erweise
    1.16
    acks
    1.13
    ullivan
    1.10
    rings
    1.09
    hearted
    1.06
    брита
    1.05
    uss
    1.04
    you
    1.04
    tower
    1.04
    laden
    1.03
    Activations Density 0.380%

    No Known Activations