© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 44315
    Prev
    Next
    INDEX
    Explanations

    uses of things

    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
    C
    0.82
    ž
    0.82
    一
    0.79
     It
    0.75
    得
    0.71
    κ
    0.71
     On
    0.70
    ט
    0.70
    ä
    0.69
    L
    0.68
    POSITIVE LOGITS
    ו
    0.94
     Uses
    0.90
    ת
    0.87
    <0x0D>
    0.84
    ة
    0.83
    ין
    0.79
     TRANSPORTURI
    0.79
     істори
    0.77
    Uses
    0.76
     CORPER
    0.75
    Activations Density 0.003%

    No Known Activations