© 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. 1446
    Prev
    Next
    INDEX
    Explanations

    I hope X

    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
    1.59
    }\
    1.44
    K
    1.42
    ARM
    1.41
     abolished
    1.41
    ET
    1.37
    stituted
    1.35
    TGF
    1.34
    ⮚
    1.32
    EL
    1.31
    POSITIVE LOGITS
    ين
    2.28
    ان
    1.63
    انة
    1.47
    ingly
    1.46
    il
    1.38
    ской
    1.38
    स
    1.38
    ፨
    1.36
    นี่
    1.35
    า
    1.34
    Activations Density 0.013%

    No Known Activations