© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 16918
    Prev
    Next
    INDEX
    Explanations

    list items or common units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    如果是
    0.53
     if
    0.49
    n
    0.46
     If
    0.45
    $
    0.41
    If
    0.41
     rename
    0.41
    j
    0.39
    rait
    0.39
    если
    0.39
    POSITIVE LOGITS
     ngang
    0.49
    istischen
    0.47
     antipode
    0.46
    𐰑
    0.45
    玹
    0.45
    🎵
    0.44
     bersama
    0.43
     കുടുംബ
    0.43
     ಕಂಪ
    0.43
     पर्यवे
    0.43
    Activations Density 0.000%

    No Known Activations