© 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. 234813
    Prev
    Next
    INDEX
    Explanations

    special price

    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
    鈁
    0.50
     begins
    0.47
    ασία
    0.47
    یکیشن
    0.46
     Affordable
    0.44
     firsthand
    0.44
     অপ্রত্যাশিত
    0.44
    কিন্ত
    0.43
     দূরের
    0.43
    成为
    0.42
    POSITIVE LOGITS
    ש
    0.50
     procent
    0.49
    UM
    0.49
    COD
    0.48
    mim
    0.47
    m
    0.47
     וי
    0.45
    AM
    0.45
    et
    0.45
    TER
    0.44
    Activations Density 0.001%

    No Known Activations