© 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. 76387
    Prev
    Next
    INDEX
    Explanations

    listing different versions

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

    entitlement year, lap number, spaces, shared goals, locale

    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
    l
    0.54
    t
    0.51
    h
    0.50
    Decision
    0.49
    >{
    0.47
    Miscellaneous
    0.46
    Youth
    0.45
    Hour
    0.45
    Quota
    0.44
    Northern
    0.44
    POSITIVE LOGITS
     själv
    0.50
     көзге
    0.48
     تعریف
    0.46
     ciência
    0.45
    ﮄ
    0.45
     nā
    0.45
    šenje
    0.43
     namam
    0.43
     împre
    0.43
     کل
    0.42
    Activations Density 0.000%

    No Known Activations