© 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. 115680
    Prev
    Next
    INDEX
    Explanations

    loan modifications

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

    explaining tokens and language structures

    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
    ારીખ
    0.53
    ８
    0.51
     ALL
    0.49
     democrat
    0.46
     CTE
    0.46
     INSTIT
    0.46
     EVERYTHING
    0.46
    все
    0.45
     ITS
    0.45
     EVERY
    0.44
    POSITIVE LOGITS
     বলিয়
    0.44
    镖
    0.43
    )}\
    0.43
    anqu
    0.43
    烧
    0.43
    iy
    0.42
     Tử
    0.42
    িয়
    0.41
     phiếu
    0.41
    ız
    0.40
    Activations Density 0.000%

    No Known Activations