© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 239801
    Prev
    Next
    INDEX
    Explanations

    simple success

    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
    Negative Logits
    т
    0.58
     sobering
    0.48
    ững
    0.47
    명
    0.47
    명이
    0.45
     intensive
    0.45
    வர்
    0.44
     confronts
    0.44
     неожидан
    0.44
     intense
    0.43
    POSITIVE LOGITS
     SUCCESS
    0.52
    ?:
    0.48
     Success
    0.47
    :]
    0.46
    :_
    0.46
    :.
    0.45
     δυ
    0.44
    TWI
    0.43
     Vote
    0.43
    llrp
    0.43
    Activations Density 0.000%

    No Known Activations