© 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. 186814
    Prev
    Next
    INDEX
    Explanations

    foreign characters

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

    endless, fundamentally, extensions, belief, game

    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
    et
    0.49
    ethe
    0.43
    ɢ
    0.43
    ized
    0.41
    iance
    0.41
    lent
    0.41
    tul
    0.40
    arag
    0.40
    stattung
    0.39
    е
    0.39
    POSITIVE LOGITS
     sparen
    0.48
     Maugin
    0.47
    🖊
    0.45
     sbParams
    0.44
     පළ
    0.43
     creates
    0.43
     പ്രവര്‍ത്തന
    0.42
    啬
    0.42
     tạo
    0.42
     tên
    0.42
    Activations Density 0.001%

    No Known Activations