© 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. 226537
    Prev
    Next
    INDEX
    Explanations

    groups of things

    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
     “‘
    0.54
     върху
    0.47
     הק
    0.46
    ídu
    0.45
     tuberc
    0.45
    ának
    0.45
     chất
    0.45
     éléments
    0.45
     젊
    0.45
     círculo
    0.44
    POSITIVE LOGITS
     picks
    0.52
    group
    0.49
     grup
    0.48
    gable
    0.47
    開
    0.45
     GROUP
    0.44
    GROUP
    0.44
    ോള
    0.44
    拾
    0.43
    gles
    0.43
    Activations Density 0.001%

    No Known Activations