© 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. 8310
    Prev
    Next
    INDEX
    Explanations

    25 best units

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

    numbers often followed by other numbers

    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
    Negative Logits
    ט
    0.49
    昰
    0.48
    卑
    0.45
    ng
    0.43
    ؤ
    0.42
    晞
    0.41
    ItemId
    0.41
    ل
    0.40
     denk
    0.39
    知名
    0.39
    POSITIVE LOGITS
     paraphr
    0.50
     asked
    0.48
    is
    0.46
    oine
    0.45
    िशन
    0.44
     annivers
    0.44
    றும்
    0.44
     paraphrase
    0.44
     percentile
    0.44
     goldfish
    0.44
    Activations Density 0.135%

    No Known Activations