© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 99183
    Prev
    Next
    INDEX
    Explanations

    platforms, services, and lists

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

    what you do or don't do

    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
     出
    0.46
    也
    0.44
     ooit
    0.41
     неко
    0.41
     algún
    0.41
     hyvin
    0.41
    uent
    0.40
    EtOH
    0.40
    개발
    0.40
     biosolids
    0.40
    POSITIVE LOGITS
    Deutsch
    0.63
     empêcher
    0.48
     collabor
    0.47
    ▶
    0.47
    Germany
    0.46
    Claude
    0.45
     συνεργ
    0.45
    Ё
    0.45
     impuls
    0.44
     Nxe
    0.44
    Activations Density 0.001%

    No Known Activations