© 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. 8275
    Prev
    Next
    INDEX
    Explanations

    specific phrases and names

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

    dosage of

    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
     küçük
    0.40
     வகைகள்
    0.40
    ֔
    0.40
    ֗
    0.39
     duniya
    0.38
     típico
    0.38
     piccola
    0.38
     Agustus
    0.38
     صغيرة
    0.37
    ֑
    0.37
    POSITIVE LOGITS
    ฯ
    0.39
    嵯
    0.39
    rir
    0.37
    ˌ
    0.36
    ঃ
    0.35
     exacerbate
    0.33
    mnt
    0.33
    凰
    0.33
     ",
    0.32
    quilibrium
    0.32
    Activations Density 0.484%

    No Known Activations