© 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. 24-GEMMASCOPE-2-RES-262K
    7. 4487
    Prev
    Next
    INDEX
    Explanations

    code comments and function returns

    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_24_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
    Ẫ
    0.48
    <0xD8>
    0.43
    წიფ
    0.41
    
    0.41
    iculares
    0.41
     가진
    0.41
    。[
    0.41
    ⿷
    0.40
    ƾ
    0.40
     شرطونو
    0.40
    POSITIVE LOGITS
    if
    0.63
    //
    0.48
    #
    0.45
     свою
    0.44
     if
    0.42
    ul
    0.42
     своем
    0.42
    this
    0.41
     своей
    0.40
     swoją
    0.40
    Activations Density 0.058%

    No Known Activations