© 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. 223657
    Prev
    Next
    INDEX
    Explanations

    nfl rams, champion hoodie, teeth whitening

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

    symbiote

    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
    ندہ
    0.48
    ません
    0.45
    ੋ
    0.43
    CapsLock
    0.40
    اندی
    0.40
    ោះ
    0.40
    MON
    0.40
    ボックス
    0.40
    积
    0.39
     力
    0.39
    POSITIVE LOGITS
    ü
    0.51
    ’-
    0.48
     পাট
    0.48
     préférence
    0.47
    ῶ
    0.47
    in
    0.47
    and
    0.47
     கரிம
    0.47
    w
    0.47
    eksiyon
    0.46
    Activations Density 0.000%

    No Known Activations