© 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. 246955
    Prev
    Next
    INDEX
    Explanations

    planning and decisions

    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
     बटे
    0.45
     breakfast
    0.44
    क्रोस
    0.44
     heartily
    0.43
    かん
    0.43
     मुफ्त
    0.42
     flowing
    0.42
    ኘ
    0.42
    𝒋
    0.41
     निम्न
    0.41
    POSITIVE LOGITS
    意味着
    0.46
     sconf
    0.45
     compromiso
    0.44
     sacrificio
    0.43
    افي
    0.43
     projeto
    0.43
    TRACE
    0.43
    合った
    0.42
     võ
    0.41
     گئیں
    0.41
    Activations Density 0.002%

    No Known Activations