© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 126580
    Prev
    Next
    INDEX
    Explanations

    command execution and data loading

    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
     wiederum
    0.54
    ıları
    0.51
    었
    0.48
     characterise
    0.45
    过来的
    0.45
    이었다
    0.45
     Revenues
    0.44
     Been
    0.44
     schließlich
    0.44
     построил
    0.43
    POSITIVE LOGITS
    iyev
    0.49
    ɡ
    0.46
    swear
    0.46
    ricts
    0.46
    GFR
    0.46
    ∝
    0.46
    lasting
    0.45
    shaus
    0.45
    σ
    0.45
    nect
    0.43
    Activations Density 0.000%

    No Known Activations