© 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. 16-GEMMASCOPE-2-RES-262K
    7. 31691
    Prev
    Next
    INDEX
    Explanations

    planter box

    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
    U
    0.61
    Globalization
    0.59
    Session
    0.57
    Monitor
    0.57
    ON
    0.56
    ED
    0.55
    Verify
    0.55
    Q
    0.54
    Stere
    0.54
    .
    0.54
    POSITIVE LOGITS
    ن
    0.73
    n
    0.63
    ק
    0.59
    น
    0.58
    ని
    0.52
     planters
    0.51
    न
    0.51
    н
    0.50
    মন্দ
    0.50
     planter
    0.49
    Activations Density 0.000%

    No Known Activations