© 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. 32798
    Prev
    Next
    INDEX
    Explanations

    an opponent

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

    alternatives or", "

    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
     Araújo
    0.44
    㡚
    0.43
    格外
    0.42
    Roxy
    0.41
    một
    0.41
    特殊的
    0.40
    橑
    0.40
    होत
    0.39
     самую
    0.39
    啶
    0.39
    POSITIVE LOGITS
     jotka
    0.53
     dnes
    0.48
     veya
    0.47
     テーブル
    0.46
     darunter
    0.46
     yoki
    0.45
    urities
    0.45
     nebo
    0.45
    errors
    0.44
     อนุ
    0.44
    Activations Density 0.000%

    No Known Activations