© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 2949
    Prev
    Next
    INDEX
    Explanations

    code examples and technical descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
    рет
    1.11
     [\
    1.09
     инде
    0.98
     (-\
    0.98
    IVERY
    0.96
     ATG
    0.94
     [%
    0.91
    ;',
    0.88
    aaf
    0.87
     Ztg
    0.87
    POSITIVE LOGITS
    <blockquote>
    2.25
     pseudos
    1.69
    section
    1.61
    <h2>
    1.61
     Pirelli
    1.59
    Sections
    1.59
    eworthy
    1.59
     Frankenstein
    1.58
     Moab
    1.57
    <h3>
    1.56
    Activations Density 0.001%

    No Known Activations