© 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. 192402
    Prev
    Next
    INDEX
    Explanations

    excessive blur

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

    cooking and food preparation

    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
    দ্বীপ
    0.44
    ibusdam
    0.42
    ่
    0.42
     luglio
    0.42
    এব
    0.41
    经历
    0.41
    誓
    0.41
    耻
    0.41
    律
    0.40
    рите
    0.40
    POSITIVE LOGITS
     erythe
    0.55
    GULD
    0.52
     rmse
    0.51
     antisymmetric
    0.46
     allyl
    0.46
     inflamm
    0.46
    OGND
    0.45
     reheating
    0.45
     Ambul
    0.45
     homotopic
    0.44
    Activations Density 0.001%

    No Known Activations