© 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. 104828
    Prev
    Next
    INDEX
    Explanations

    don't you dare

    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
    0.71
    t
    0.70
    P
    0.67
    M
    0.64
    X
    0.63
    L
    0.62
    E
    0.61
     M
    0.60
    T
    0.60
     -
    0.58
    POSITIVE LOGITS
     malicious
    0.54
     божо
    0.54
     особливо
    0.53
    ufig
    0.53
     దృష్టి
    0.52
    దవ
    0.52
     ಕೆಲವು
    0.51
     sarebbero
    0.50
     själv
    0.50
     성능
    0.50
    Activations Density 0.013%

    No Known Activations