© 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. 166365
    Prev
    Next
    INDEX
    Explanations

    services provided by

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

    command-line interface, Plexus, Hacker

    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
     Steinberg
    0.47
     as
    0.43
     (
    0.43
     Stern
    0.43
     Niem
    0.41
     Hoek
    0.41
     Barb
    0.41
    time
    0.41
     Clerk
    0.40
     Wiel
    0.40
    POSITIVE LOGITS
    ர்
    0.56
    ر
    0.56
    ב
    0.55
    ત
    0.54
    ર
    0.54
    ي
    0.52
    uelva
    0.51
     importar
    0.51
     envío
    0.50
     destacado
    0.49
    Activations Density 0.001%

    No Known Activations