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

    Neuronpedia

    Jacobian LensNEW
    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. 88618
    Prev
    Next
    INDEX
    Explanations

    floor or ground

    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
    ب
    0.74
     Skin
    0.65
     sepol
    0.64
     കുട്ട
    0.63
    溃
    0.63
    0.62
     CTRL
    0.61
    Ку
    0.60
    К
    0.60
     देखें
    0.59
    POSITIVE LOGITS
    pesar
    0.69
    pointee
    0.61
    mittedly
    0.57
    khidmat
    0.57
    ños
    0.55
    шуу
    0.55
    ha
    0.54
    mares
    0.53
    isc
    0.52
     appropriations
    0.52
    Activations Density 0.003%

    No Known Activations