© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8538
    Prev
    Next
    INDEX
    Explanations

    frazier and francois

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

    fraction and formula formatting

    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_40_width_16k_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
    Cre
    0.40
    ދ
    0.40
    rène
    0.39
    mour
    0.38
     sekä
    0.38
    バイス
    0.37
     aspectos
    0.37
    HIGHLIGHT
    0.37
    നേ
    0.36
    érer
    0.36
    POSITIVE LOGITS
     bevel
    0.44
    {}{
    0.43
     깜
    0.40
     Ather
    0.39
     solid
    0.37
    馊
    0.37
     snow
    0.36
    iap
    0.36
     Bernoulli
    0.36
    IDAE
    0.36
    Activations Density 0.022%

    No Known Activations