© 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. 71089
    Prev
    Next
    INDEX
    Explanations

    time or dates

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

    phrases following noun/adjective

    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
    ш
    0.57
    ش
    0.53
    ch
    0.52
    l
    0.50
    ল
    0.50
    ва
    0.50
    Ρ
    0.49
    <0xB9>
    0.48
    יר
    0.48
    рко
    0.46
    POSITIVE LOGITS
     увеличения
    0.58
     ocasion
    0.54
     increases
    0.54
     اُن
    0.47
     अरे
    0.47
     excès
    0.46
     aumentar
    0.46
     üzerine
    0.46
     breaches
    0.46
     нарушения
    0.46
    Activations Density 0.000%

    No Known Activations