© 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. 8161
    Prev
    Next
    INDEX
    Explanations

    url query parameters

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

    URL keys and parameters

    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
    Communications
    0.40
     surging
    0.39
    Metadata
    0.38
    рга
    0.38
    риа
    0.38
    Papers
    0.38
     Endocr
    0.37
     एकूण
    0.37
     Gears
    0.36
    论
    0.36
    POSITIVE LOGITS
    lang
    0.61
     lang
    0.56
    utm
    0.56
    q
    0.52
     q
    0.51
    format
    0.51
    _=
    0.51
    mode
    0.48
    Lang
    0.48
     Lang
    0.48
    Activations Density 0.014%

    No Known Activations