© 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. 31-GEMMASCOPE-2-RES-262K
    7. 27098
    Prev
    Next
    INDEX
    Explanations

    Recommended for

    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_31_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
    躡
    0.55
    akkhati
    0.54
    栥
    0.53
    '।
    0.52
    물이
    0.52
    '
    0.52
    возможно
    0.52
    pengaruhi
    0.51
    क
    0.51
     участия
    0.50
    POSITIVE LOGITS
     by
    0.67
     to
    0.61
     on
    0.59
     for
    0.55
    on
    0.49
     because
    0.48
    لاست
    0.47
     from
    0.47
     för
    0.46
     perchè
    0.45
    Activations Density 0.023%

    No Known Activations