© 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. 147471
    Prev
    Next
    INDEX
    Explanations

    results, funding, deficit, design, blame

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

    email cover letter, signature look

    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
    廨
    0.52
     ポー
    0.47
    ванням
    0.46
    തെ
    0.46
    п
    0.46
    וכ
    0.45
    邦
    0.44
     रक्कम
    0.43
    ag
    0.42
     Правда
    0.42
    POSITIVE LOGITS
     laboratory
    0.52
     flu
    0.46
     lab
    0.44
     advers
    0.43
     sensibly
    0.41
     λ
    0.41
     confidently
    0.41
     adversely
    0.40
     facilité
    0.40
     reheating
    0.39
    Activations Density 0.001%

    No Known Activations