© 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. 136009
    Prev
    Next
    INDEX
    Explanations

    but you, service, contact

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

    describing actions or goals

    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
     גי
    0.48
     ليست
    0.47
    ва
    0.46
    
    0.46
    កំព
    0.45
    動
    0.45
    術
    0.44
    キーワード
    0.44
    蛍
    0.43
     Шу
    0.42
    POSITIVE LOGITS
     regalías
    0.52
    एसआय
    0.50
     dış
    0.49
     প্রাপ্য
    0.49
     establecidos
    0.47
    ču
    0.47
    Thats
    0.46
     fracciones
    0.46
    प्ट
    0.46
     estabele
    0.46
    Activations Density 0.000%

    No Known Activations