© 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. 215940
    Prev
    Next
    INDEX
    Explanations

    Airline tickets, money, house, venture, BOOLE

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

    permissive, burn, define, synthetic, knowing, puff

    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
     thăm
    0.49
    arms
    0.48
    face
    0.48
     تعلیم
    0.48
     nale
    0.45
    time
    0.45
    biotic
    0.44
     ฝ
    0.44
    लैंड
    0.44
    hotels
    0.44
    POSITIVE LOGITS
    鶉
    0.47
    IList
    0.45
     cyclin
    0.45
     MACHINIST
    0.44
    CZ
    0.44
    隧
    0.44
    ਬਰ
    0.42
    耷
    0.42
    idP
    0.41
     महिलाओ
    0.41
    Activations Density 0.000%

    No Known Activations