© 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. 130183
    Prev
    Next
    INDEX
    Explanations

    reporting or evaluating

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

    explicitly asking for or describing

    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
    況
    0.45
    ResultMessage
    0.43
     receivables
    0.42
    在
    0.41
    ness
    0.41
    ste
    0.40
    dee
    0.40
     receipts
    0.40
    sten
    0.40
    》。
    0.40
    POSITIVE LOGITS
     Technische
    0.55
     Ти
    0.50
    𒋫
    0.48
     Erfahr
    0.48
     కరో
    0.47
     Bibliothek
    0.47
     bauen
    0.46
     Teknologi
    0.45
    Technische
    0.45
     endlich
    0.45
    Activations Density 0.000%

    No Known Activations