© 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. 108178
    Prev
    Next
    INDEX
    Explanations

    list items and headings

    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
     Velcro
    0.52
     neque
    0.51
     elm
    0.47
     crochet
    0.47
    وترات
    0.46
     buckle
    0.46
    .[/
    0.46
     IGBT
    0.44
     croche
    0.43
     Crochet
    0.43
    POSITIVE LOGITS
    '
    0.46
    ми
    0.45
    ट
    0.45
    ラ
    0.44
    žia
    0.44
    тин
    0.43
    작
    0.43
    モー
    0.42
    пус
    0.42
    して
    0.41
    Activations Density 0.008%

    No Known Activations