© 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. 3458
    Prev
    Next
    INDEX
    Explanations

    instructions and explanations

    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
    ।
    1.09
    IS
    0.89
    i
    0.88
    RA
    0.86
    .
    0.86
    。
    0.86
    you
    0.83
    ется
    0.82
    ។
    0.81
     veineux
    0.78
    POSITIVE LOGITS
    고
    1.03
    ↵↵
    0.75
    و
    0.69
    ?
    0.68
    )
    0.68
    '
    0.66
    使
    0.65
    евич
    0.64
    ه
    0.64
     звез
    0.63
    Activations Density 1.092%

    No Known Activations