© 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. 261185
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    あった
    0.43
    is
    0.41
    ды
    0.41
    zuki
    0.41
    フォード
    0.41
    us
    0.40
    Ἀ
    0.40
    ード
    0.40
    apd
    0.40
    bones
    0.40
    POSITIVE LOGITS
     fün
    0.54
     दक्षिण
    0.50
     sempl
    0.49
     crít
    0.47
    以内
    0.46
     součas
    0.46
     छठे
    0.46
    堞
    0.46
     passar
    0.45
     Simpl
    0.45
    Activations Density 0.001%

    No Known Activations