© 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. 38734
    Prev
    Next
    INDEX
    Explanations

    jira tickets and tools

    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
    il
    1.81
    ح
    1.77
    م
    1.63
    ल
    1.45
    le
    1.41
    la
    1.38
    r
    1.36
    se
    1.33
    rary
    1.30
    Τα
    1.30
    POSITIVE LOGITS
     maroon
    1.20
    ваме
    1.19
    ৩৬
    1.17
    UIServer
    1.17
     macaroni
    1.17
     looser
    1.17
    ים
    1.16
    aun
    1.14
     겁니다
    1.13
     שלנו
    1.13
    Activations Density 0.017%

    No Known Activations