© 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. 250508
    Prev
    Next
    INDEX
    Explanations

    gallery, category, drawing, or containment

    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
    𝙼
    0.49
     زمان
    0.48
    మైన
    0.48
     آزمایش
    0.47
     kadang
    0.46
     ای
    0.46
     स्वच्छ
    0.46
     hampir
    0.46
    ﺫ
    0.46
     صبح
    0.46
    POSITIVE LOGITS
    érées
    0.47
    стрі
    0.46
    ！）
    0.45
    пикир
    0.45
    娉
    0.44
    rées
    0.44
     žiad
    0.43
    নাত
    0.42
    филлер
    0.42
    য্
    0.42
    Activations Density 0.002%

    No Known Activations