© 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. 226710
    Prev
    Next
    INDEX
    Explanations

    collocations and phrases

    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
     openness
    0.46
     Pythagorean
    0.46
     Walth
    0.46
     gentle
    0.45
     Waver
    0.45
     Transformations
    0.45
     Beethoven
    0.44
    ссив
    0.44
     knobs
    0.44
    岭
    0.44
    POSITIVE LOGITS
    PRODUCT
    0.51
     народа
    0.50
    ürt
    0.50
    জেল
    0.50
    ):
    0.49
    HAR
    0.48
     款
    0.47
     incluidas
    0.47
     單
    0.47
     conformidad
    0.46
    Activations Density 0.000%

    No Known Activations