© 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. 70061
    Prev
    Next
    INDEX
    Explanations

    for installations, free, homes, Alabama, meetings

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

    monolithic, single, large, best, extremely

    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
     Hau
    0.52
     ㅏ
    0.48
     ଚ
    0.47
     た
    0.46
     pearl
    0.46
     السالب
    0.46
     も
    0.45
     auc
    0.45
     q
    0.45
    ケ
    0.44
    POSITIVE LOGITS
    Unlock
    0.51
    Solution
    0.50
    स्तरीय
    0.49
    荡
    0.49
    卫生
    0.47
    杀
    0.46
    Fear
    0.46
    视野
    0.46
    లు
    0.46
    दिल्ली
    0.46
    Activations Density 0.000%

    No Known Activations