© 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. 245802
    Prev
    Next
    INDEX
    Explanations

    select words found after certain tokens

    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
    intis
    0.47
     فو
    0.45
     усі
    0.44
    ാ
    0.44
     sacks
    0.43
     delic
    0.42
     كافة
    0.42
    alve
    0.41
    ald
    0.40
     بالت
    0.40
    POSITIVE LOGITS
     pasaj
    0.49
    杣
    0.46
    テーブル
    0.46
    を見ると
    0.46
    คุณ
    0.46
    ёл
    0.46
     Excel
    0.46
     നമ്പർ
    0.45
     emocionante
    0.45
    ருக்கு
    0.45
    Activations Density 0.000%

    No Known Activations