© 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. 44919
    Prev
    Next
    INDEX
    Explanations

    mutable references

    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
    원
    1.19
    서
    1.04
     aucun
    1.01
     pénétr
    0.96
    슨
    0.96
     nello
    0.94
     toute
    0.93
    сть
    0.92
    있는
    0.92
     দূর
    0.92
    POSITIVE LOGITS
    ه
    1.39
    ে
    1.27
    ร
    1.22
    د
    1.18
     Rü
    1.14
    Rub
    1.13
    selves
    1.10
     ETC
    1.06
     EHR
    1.06
     COE
    1.04
    Activations Density 0.001%

    No Known Activations