© 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. 187147
    Prev
    Next
    INDEX
    Explanations

    requests, requests, new photos, effort, hon, allow, June, like

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

    calculates distances, wanted improvements, stop alerts

    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
     slang
    0.48
     ტ
    0.46
    ['
    0.44
     vocabulary
    0.44
     circus
    0.44
    ress
    0.43
     behavior
    0.42
     reun
    0.42
     ט
    0.42
     examination
    0.41
    POSITIVE LOGITS
    kala
    0.59
    আল্লাহ
    0.48
    ITATION
    0.48
     Correlation
    0.47
    กก
    0.45
     aumentare
    0.45
    attractive
    0.44
     migliorare
    0.44
     baada
    0.44
     ব্যবস্থাপ
    0.43
    Activations Density 0.000%

    No Known Activations