© 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-IT
    3. 41-GEMMASCOPE-2-RES-262K
    4. 57241
    Prev
    Next
    INDEX
    Explanations

    legal and ethical analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    0.41
    (*
    0.40
    <html>
    0.39
     (*
    0.39
     +.
    0.39
    가능
    0.39
    idere
    0.38
     (+
    0.38
    unal
    0.37
    thest
    0.37
    POSITIVE LOGITS
     consort
    0.44
     anggota
    0.43
     earnest
    0.41
     naughty
    0.39
    accio
    0.38
     charisma
    0.38
     Accompl
    0.38
     handful
    0.37
     Pars
    0.37
     Peacock
    0.37
    Activations Density 0.000%

    No Known Activations