© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11275
    Prev
    Next
    INDEX
    Explanations

    pandas DataFrame and DataSet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acing
    0.49
    atan
    0.47
     숫
    0.46
    ently
    0.46
    acketing
    0.45
    直径
    0.45
    čku
    0.44
    akk
    0.43
    den
    0.42
    ell
    0.42
    POSITIVE LOGITS
    ه
    0.55
     dataSource
    0.51
    хта
    0.51
     datasets
    0.50
     базы
    0.50
     DataSource
    0.50
    া
    0.49
     datasource
    0.49
     Bac
    0.47
     DataSet
    0.46
    Activations Density 0.039%

    No Known Activations