© 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. 16-GEMMASCOPE-2-RES-262K
    4. 9191
    Prev
    Next
    INDEX
    Explanations

    Material Design

    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_16_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
     e
    0.61
     unknowingly
    0.59
     arid
    0.58
     inadvertently
    0.57
     ngôn
    0.57
     enlarging
    0.55
     turnkey
    0.55
     coast
    0.54
     comedies
    0.54
     προσ
    0.53
    POSITIVE LOGITS
    ים
    0.59
    ی
    0.58
    ண்கள்
    0.56
     Ці
    0.56
    ר
    0.56
    щи
    0.55
    マ
    0.55
    sample
    0.55
    р
    0.55
    ობა
    0.54
    Activations Density 0.003%

    No Known Activations