© 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. 1521
    Prev
    Next
    INDEX
    Explanations

    thorny or thorns

    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
    ิน
    0.74
    耖
    0.71
    करण
    0.66
    ítani
    0.65
    ство
    0.64
     CGFloat
    0.64
    ністю
    0.63
    䉽
    0.63
     Gwyn
    0.62
    寯
    0.62
    POSITIVE LOGITS
     thorn
    0.94
     thorns
    0.93
    l
    0.79
    i
    0.78
    棘
    0.77
     thorny
    0.75
    lara
    0.71
    on
    0.64
    lardan
    0.63
    0.63
    Activations Density 0.007%

    No Known Activations