© 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. 149324
    Prev
    Next
    INDEX
    Explanations

    one fumble

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

    law, faith, termination, interaction

    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
     ብዙ
    0.46
     ガー
    0.45
     twórc
    0.45
     întâm
    0.45
    化工
    0.43
     tathapi
    0.43
     ফা
    0.43
    鬼
    0.43
    長さ
    0.42
    蒟
    0.42
    POSITIVE LOGITS
    பால்
    0.51
    мян
    0.44
     specifying
    0.44
    డిన
    0.43
    with
    0.43
     heredit
    0.42
     challengers
    0.42
    ैश
    0.41
    сум
    0.41
    olis
    0.40
    Activations Density 0.001%

    No Known Activations