© 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. 115277
    Prev
    Next
    INDEX
    Explanations

    foreign words or specific languages

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

    geothermal vents, ML models, appointments

    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
    tty
    0.51
    COS
    0.49
    établir
    0.48
    -/
    0.47
    cessing
    0.47
    SOD
    0.47
    ⁄
    0.47
    osin
    0.47
    ０
    0.47
    \
    0.47
    POSITIVE LOGITS
     چنین
    0.46
     في
    0.45
     suyo
    0.44
     landlab
    0.44
     dejado
    0.44
     cuya
    0.43
     llu
    0.43
     suele
    0.43
     blades
    0.43
     jeszcze
    0.43
    Activations Density 0.001%

    No Known Activations