© 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. 129845
    Prev
    Next
    INDEX
    Explanations

    formal contexts

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

    conversational opening phrases

    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
    老的
    0.48
    Brown
    0.46
    Been
    0.44
    Metrics
    0.43
     efficiencies
    0.43
    යක්
    0.43
    猞
    0.43
    Mountain
    0.42
    ether
    0.41
    Ther
    0.41
    POSITIVE LOGITS
     ২
    0.53
    ](./
    0.52
     prochaine
    0.50
     က
    0.50
     σχε
    0.48
     fordi
    0.48
    (/^
    0.48
     prossima
    0.48
     短
    0.48
     فيلم
    0.48
    Activations Density 0.000%

    No Known Activations