© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 39187
    Prev
    Next
    INDEX
    Explanations

    special ability or nutritious food

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

    shaped area, wider than

    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
    Not in Any Lists

    No Comments

    Negative Logits
    5
    0.55
    ５
    0.55
    1
    0.54
    ні
    0.52
     only
    0.52
    ನ್
    0.50
    １
    0.50
    Ｎ
    0.49
    не
    0.47
     vasta
    0.46
    POSITIVE LOGITS
     கீழ
    0.46
     книга
    0.44
     機械
    0.44
     Burke
    0.43
     lát
    0.43
     কণ
    0.42
    lád
    0.42
     जागरूकता
    0.41
    باً
    0.41
     बालकनियां
    0.40
    Activations Density 0.000%

    No Known Activations