© 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. 205227
    Prev
    Next
    INDEX
    Explanations

    flower arrangements, refunds, enthusiastic recipient

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

    common grammatical constructions

    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
    ite
    0.60
    in
    0.57
    ending
    0.56
    é
    0.56
    ect
    0.55
    ife
    0.54
    ate
    0.53
    ás
    0.53
    est
    0.52
    elle
    0.52
    POSITIVE LOGITS
    说过
    0.50
    意思是
    0.48
     negozio
    0.47
    ⓪
    0.47
     Galileo
    0.46
    ১২শ
    0.46
     microSD
    0.46
    やや
    0.46
    ディズニー
    0.46
     regarder
    0.45
    Activations Density 0.001%

    No Known Activations