© 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. 250519
    Prev
    Next
    INDEX
    Explanations

    talk to him, this evening, early release

    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
    x
    0.47
    Feedback
    0.43
    [
    0.43
    Nep
    0.43
    คำ
    0.43
    cia
    0.42
    Func
    0.42
    Contribution
    0.42
    Management
    0.41
    Knight
    0.41
    POSITIVE LOGITS
     гео
    0.54
     внутри
    0.53
     ৷
    0.52
     пери
    0.50
    uiden
    0.50
     온도
    0.49
     frutto
    0.49
     كر
    0.49
     високо
    0.49
     관련된
    0.49
    Activations Density 0.000%

    No Known Activations