© 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. 152825
    Prev
    Next
    INDEX
    Explanations

    vegan food

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

    Chorus, loan transfer, chess rules

    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
    ？
    0.51
    节目
    0.50
    钠
    0.48
    马上
    0.45
    "
    0.45
    对照
    0.45
    𝕕
    0.45
    !).
    0.44
    éry
    0.44
    $
    0.43
    POSITIVE LOGITS
     ব্রাজ
    0.49
     sempat
    0.48
     understated
    0.48
     গ
    0.48
     apertura
    0.47
     nascost
    0.47
     abierta
    0.46
     rationality
    0.46
     გავ
    0.46
     posizione
    0.45
    Activations Density 0.000%

    No Known Activations