© 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. 6166
    Prev
    Next
    INDEX
    Explanations

    Twilight Sparkle, Taylor Swift

    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
    2
    0.87
    oirs
    0.81
    ла
    0.75
    erede
    0.73
    delen
    0.71
    iar
    0.70
    eningen
    0.70
    eli
    0.70
    دا
    0.69
    -
    0.68
    POSITIVE LOGITS
    in
    1.32
    ک
    1.12
    O
    1.03
    க
    0.99
    し
    0.99
     demarc
    0.95
    に
    0.93
     familiarize
    0.90
    возможно
    0.90
     dwind
    0.89
    Activations Density 0.003%

    No Known Activations