© 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. 34801
    Prev
    Next
    INDEX
    Explanations

    verbal, look, more, site, great, keynote

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

    search intent and function

    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
    ༢
    0.54
    CASE
    0.52
    ETERS
    0.52
    CHAPTER
    0.51
    )
    0.50
    of
    0.50
    Ụ
    0.50
    ){
    0.49
    )\
    0.49
    ROLL
    0.49
    POSITIVE LOGITS
     wäre
    0.52
     wären
    0.46
     Beyond
    0.46
     ciudadano
    0.45
     SMI
    0.45
     zač
    0.44
     Enem
    0.44
     Administración
    0.44
     begann
    0.44
     aimed
    0.44
    Activations Density 0.000%

    No Known Activations