© 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. 123027
    Prev
    Next
    INDEX
    Explanations

    focus on subject

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

    non-English language indicators

    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
     தேர்ந்தெடுக்க
    0.55
     recognized
    0.51
     leak
    0.49
     "@
    0.48
     partitioning
    0.48
     partitions
    0.47
     inspection
    0.46
     leaking
    0.46
     symbolically
    0.46
     notice
    0.45
    POSITIVE LOGITS
    escent
    0.47
    ections
    0.46
    Brun
    0.46
    ayev
    0.44
    정이
    0.43
    囉
    0.43
    azos
    0.43
    cary
    0.43
    უალ
    0.43
    舂
    0.43
    Activations Density 0.000%

    No Known Activations