© 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. 16-GEMMASCOPE-2-RES-16K
    7. 559
    Prev
    Next
    INDEX
    Explanations

    mathematical or scientific terms

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

    programming constructs and grammar

    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_16_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
    :
    0.64
    I
    0.52
    ۔
    0.51
    מ
    0.47
    7
    0.46
    urine
    0.44
    ،
    0.42
    S
    0.42
    6
    0.42
    für
    0.41
    POSITIVE LOGITS
     Laplacian
    0.56
     nedenle
    0.48
    u
    0.48
     indexOf
    0.46
     Hamiltonian
    0.46
     innymi
    0.46
     Mitsubishi
    0.45
    anın
    0.45
     Fresnel
    0.45
     fáb
    0.45
    Activations Density 0.726%

    No Known Activations