© 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. 167883
    Prev
    Next
    INDEX
    Explanations

    Laser, page, obscured, cases, everywhere, multiple, defend

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

    urgent matters

    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
    clientes
    0.47
     المخت
    0.46
    핵
    0.45
     Moreira
    0.44
     회
    0.44
     населення
    0.44
     Расійскай
    0.43
    acterium
    0.43
     γεν
    0.43
    つ
    0.43
    POSITIVE LOGITS
     bookArray
    0.48
    م
    0.48
     మరి
    0.48
     Albanian
    0.46
     Princess
    0.46
     Piece
    0.46
     Spanish
    0.46
     varsa
    0.46
     Allergy
    0.45
    is
    0.44
    Activations Density 0.000%

    No Known Activations