© 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. 166660
    Prev
    Next
    INDEX
    Explanations

    saves lives, provisions, short questions

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

    describing media and conditions

    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
    দিকে
    0.48
     wasting
    0.45
     sekarang
    0.43
    kh
    0.43
    d
    0.42
    s
    0.41
     hoeveel
    0.41
    ہ
    0.40
     hourly
    0.40
     faucet
    0.40
    POSITIVE LOGITS
     स्लाइड्स
    0.48
    Biod
    0.47
    랫폼
    0.46
     బు
    0.46
     प्रीत
    0.46
    études
    0.46
     মামলায়
    0.46
    includ
    0.45
    🎿
    0.44
     মাহ
    0.44
    Activations Density 0.000%

    No Known Activations