© 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. 161975
    Prev
    Next
    INDEX
    Explanations

    manage, toggle, odds, dive, acquire

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

    security events

    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
    le
    0.61
    conti
    0.54
    und
    0.54
    ke
    0.52
     mite
    0.51
    л
    0.51
     spread
    0.51
     กรณี
    0.50
     fa
    0.50
    sit
    0.50
    POSITIVE LOGITS
     Estad
    0.47
     современном
    0.46
     وقت
    0.45
     Colombie
    0.45
     disponibilités
    0.44
     Xml
    0.44
    驒
    0.44
     ভবিষ্য
    0.43
     viagem
    0.43
    atschapp
    0.43
    Activations Density 0.000%

    No Known Activations