© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 25114
    Prev
    Next
    INDEX
    Explanations

    Vigenère chip item monomers Dynamic based distributed

    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
     intestinal
    0.49
     insensitive
    0.46
     hernia
    0.46
    <0x0D>
    0.46
    plot
    0.46
     intestine
    0.46
     unten
    0.45
     hypothalamus
    0.45
     exud
    0.45
     effectual
    0.45
    POSITIVE LOGITS
     thiên
    0.47
    的机会
    0.46
    طي
    0.44
    必须
    0.44
    民主
    0.44
    ອ
    0.43
    的操作
    0.43
    ヒット
    0.43
    وض
    0.43
    灯
    0.43
    Activations Density 0.000%

    No Known Activations