© 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. 592
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    numbers followed by sample or °

    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
    на
    0.58
    ก
    0.48
     similaire
    0.47
    ంగా
    0.46
     የተለያዩ
    0.46
    า
    0.45
    1
    0.45
    ра
    0.45
    ာ
    0.44
     przykład
    0.44
    POSITIVE LOGITS
     (
    0.73
    I
    0.49
     (=
    0.45
    to
    0.42
     (!
    0.39
     ((
    0.39
     =
    0.38
    ]=
    0.37
    y
    0.37
    ~(
    0.37
    Activations Density 0.479%

    No Known Activations