© 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. 56359
    Prev
    Next
    INDEX
    Explanations

    GBMHI, Autodesk, article; step-by-step

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

    future work

    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
     aeroplane
    0.44
    ޏ
    0.41
    巒
    0.40
     بينهم
    0.40
     diaphr
    0.39
    舉行
    0.39
     bungalows
    0.39
    }`);
    0.38
     الشيء
    0.37
    擋
    0.37
    POSITIVE LOGITS
     S
    0.42
     O
    0.42
     Sustainability
    0.42
    R
    0.42
     R
    0.41
     Steven
    0.41
     Sozial
    0.41
     Wenger
    0.41
     Obama
    0.40
     Valerie
    0.40
    Activations Density 0.002%

    No Known Activations