© 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. 31-GEMMASCOPE-2-RES-262K
    7. 5061
    Prev
    Next
    INDEX
    Explanations

    grid lines and separators

    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
    sez
    0.51
     oleks
    0.50
     zouden
    0.47
    нина
    0.47
    zki
    0.46
    soo
    0.46
    ",[],"
    0.46
    耋
    0.46
    _^
    0.46
    spieler
    0.45
    POSITIVE LOGITS
    MM
    0.46
    ↵
    0.43
     \
    0.43
     MM
    0.43
     rearranging
    0.41
     becoming
    0.40
     mutually
    0.39
     SK
    0.38
     SARS
    0.38
    ミング
    0.38
    Activations Density 0.020%

    No Known Activations