© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 195126
    Prev
    Next
    INDEX
    Explanations

    minerals, beauty, valley, bikini top

    np_acts-logits-general · gemini-2.5-flash-lite

    help lines and computer hardware

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    for
    1.18
     for
    1.11
    ن
    1.09
    el
    1.00
    ala
    0.95
    ah
    0.88
    dh
    0.85
    র
    0.83
    ます
    0.82
    िला
    0.82
    POSITIVE LOGITS
    u
    1.20
    ゅう
    0.99
    ו
    0.96
    uws
    0.93
    ي
    0.93
    i
    0.89
     insur
    0.88
    ா
    0.86
    ி
    0.86
    ı
    0.86
    Activations Density 4.216%

    No Known Activations