© 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. 218560
    Prev
    Next
    INDEX
    Explanations

    university reading

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

    startPaidTeamAssociate

    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
    ibul
    0.47
    0.46
    )",
    0.45
    )
    0.45
    ↵
    0.44
    過的
    0.43
     V
    0.41
    ).
    0.41
     Buck
    0.40
    最多的
    0.40
    POSITIVE LOGITS
     čet
    0.56
     نبی
    0.53
     formulaire
    0.50
     preocupa
    0.49
     名前
    0.49
    updating
    0.49
     پیغمبر
    0.49
     삭제
    0.48
    beliefs
    0.48
     호출
    0.48
    Activations Density 0.000%

    No Known Activations