© 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. 102877
    Prev
    Next
    INDEX
    Explanations

    cold drinking

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

    cooking and economics

    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
    ල්ල
    0.48
     ссылку
    0.47
    q
    0.46
    zelf
    0.45
    beginning
    0.45
    deposited
    0.44
    îne
    0.44
    DCs
    0.44
    다
    0.44
    랑
    0.43
    POSITIVE LOGITS
     redesign
    0.52
     sizeof
    0.49
     けれど
    0.49
     Margaret
    0.49
     okolic
    0.46
     steeply
    0.45
     ölç
    0.45
    💂
    0.45
    রত্ব
    0.44
     barbarian
    0.44
    Activations Density 0.000%

    No Known Activations