© 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. 85996
    Prev
    Next
    INDEX
    Explanations

    phrases indicating continuation or detail

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

    hollow shells, trans fats

    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
     bhav
    0.45
     ingest
    0.42
    í
    0.42
    互動
    0.41
    z
    0.41
    STRACT
    0.40
     இருக்கிறார்
    0.40
     excer
    0.39
    飲食
    0.39
     અનુ
    0.38
    POSITIVE LOGITS
    numOf
    0.54
    佯
    0.45
     हारा
    0.45
     crippled
    0.43
    쬐
    0.43
     olisi
    0.43
     проблемой
    0.43
     gracefully
    0.42
     serían
    0.42
     Всем
    0.42
    Activations Density 0.001%

    No Known Activations