© 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
    3. 31-GEMMASCOPE-2-RES-262K
    4. 47512
    Prev
    Next
    INDEX
    Explanations

    matching people

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

    few overseas uk projects

    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
     estará
    0.48
    лює
    0.48
     таблицу
    0.47
    форд
    0.46
    бліоте
    0.46
     خواهد
    0.46
     Fernandez
    0.46
    梸
    0.45
    㳯
    0.45
     Hofmann
    0.44
    POSITIVE LOGITS
     or
    0.55
     problems
    0.52
    uk
    0.51
    জ
    0.49
     img
    0.48
     country
    0.48
    as
    0.47
    qu
    0.47
     consist
    0.47
    ad
    0.47
    Activations Density 0.000%

    No Known Activations