© 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. 103003
    Prev
    Next
    INDEX
    Explanations

    Click

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

    Finn's lighthouse

    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
     that
    0.52
     from
    0.47
     Infrastructure
    0.46
     perforation
    0.46
     Consulting
    0.45
     Consol
    0.45
     Imped
    0.45
     Communications
    0.44
     consignment
    0.44
    獪
    0.44
    POSITIVE LOGITS
     여섯
    0.49
    ير
    0.48
    يك
    0.47
     quatro
    0.47
     cinci
    0.46
     cinco
    0.46
     vijf
    0.46
     வெப்ப
    0.45
     ثلاث
    0.44
     다섯
    0.44
    Activations Density 0.000%

    No Known Activations