© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 1543
    Prev
    Next
    INDEX
    Explanations

    skin condition and health

    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
    ۔
    0.75
    ہ
    0.68
     кораб
    0.68
    iv
    0.66
     has
    0.65
    >();
    0.65
     heeft
    0.64
    ច
    0.64
    *",
    0.64
    のもの
    0.63
    POSITIVE LOGITS
     skin
    0.95
     I
    0.93
    ur
    0.92
    Skin
    0.89
     a
    0.88
    ва
    0.86
     Skin
    0.83
    skin
    0.82
     be
    0.79
     SKIN
    0.79
    Activations Density 0.009%

    No Known Activations