© 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. 103387
    Prev
    Next
    INDEX
    Explanations

    bookmark, opener, hourglass

    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
    ’
    0.99
    id
    0.87
    if
    0.87
    for
    0.84
    au
    0.82
    b
    0.77
    ad
    0.74
     for
    0.74
    ’.
    0.73
    is
    0.72
    POSITIVE LOGITS
    ז
    0.73
    ራሉ
    0.70
    ную
    0.67
     curiously
    0.66
    קור
    0.65
    𝑔
    0.65
    зви
    0.64
    ંગ
    0.64
    gewicht
    0.63
    си
    0.63
    Activations Density 0.001%

    No Known Activations