© 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. 108053
    Prev
    Next
    INDEX
    Explanations

    subsequent hesitation, tunel, car hire

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

    metaphorical statements and expressions

    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
    <unused80>
    0.49
     mouthful
    0.47
     ისინი
    0.46
     vient
    0.46
     mathematician
    0.46
     Yugoslav
    0.45
     νο
    0.44
    ্ক
    0.44
     eo
    0.44
     satir
    0.44
    POSITIVE LOGITS
    Masters
    0.56
    t
    0.51
    Barnes
    0.50
    Bennett
    0.49
    мена
    0.48
    Servers
    0.48
    Ха
    0.48
    Werk
    0.48
    ंडे
    0.48
    рда
    0.48
    Activations Density 0.000%

    No Known Activations