© 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. 73442
    Prev
    Next
    INDEX
    Explanations

    non-english languages

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

    business, sales, website, or US interests

    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
     fuses
    0.56
    m
    0.56
     fuse
    0.50
     fusing
    0.49
    1
    0.49
     -
    0.47
    ิง
    0.47
    _-
    0.46
     killers
    0.45
     comunic
    0.45
    POSITIVE LOGITS
     많은
    0.66
     યોગ્ય
    0.53
     सप्त
    0.50
     කිරීමට
    0.50
     కార్యక్రమంలో
    0.49
    itabbo
    0.49
     ಅನೇಕ
    0.49
    piej
    0.48
     అనేక
    0.48
     일반적으로
    0.48
    Activations Density 0.000%

    No Known Activations