© 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. 144353
    Prev
    Next
    INDEX
    Explanations

    replica watches, FM radio

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

    initials and abbreviations

    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
    fen
    0.51
    vä
    0.50
     β
    0.50
     ਟ
    0.48
    ṇ
    0.47
     ecz
    0.47
     銀
    0.47
     ἐ
    0.47
    zám
    0.47
    eniz
    0.46
    POSITIVE LOGITS
    というか
    0.50
    LA
    0.49
    EP
    0.48
    SE
    0.48
    EL
    0.47
    のデザイン
    0.47
     wacky
    0.46
    AL
    0.46
    CH
    0.46
    👙
    0.46
    Activations Density 0.000%

    No Known Activations