© 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. 31-GEMMASCOPE-2-RES-262K
    7. 170515
    Prev
    Next
    INDEX
    Explanations

    passing Norman, ensure proper, lobby areas

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

    starting new steps

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    কির
    0.48
    ⇵
    0.48
     nothing
    0.47
     intercambio
    0.47
    没什么
    0.47
    没有什么
    0.46
     parallels
    0.45
     grueling
    0.45
     retomar
    0.45
     glimpses
    0.45
    POSITIVE LOGITS
    dens
    0.44
    esu
    0.43
    ders
    0.43
    atri
    0.43
    ㅊ
    0.43
     éxitos
    0.42
    ಷ್ಟು
    0.41
    द्भ
    0.41
    เร็จ
    0.41
     فوتب
    0.41
    Activations Density 0.001%

    No Known Activations