© 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. 11936
    Prev
    Next
    INDEX
    Explanations

    because

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

    causality and explanation

    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
     parfois
    0.52
    6
    0.52
     často
    0.51
    2
    0.50
    1
    0.50
    5
    0.49
    8
    0.49
    7
    0.48
    有时
    0.48
     insightful
    0.48
    POSITIVE LOGITS
     BECAUSE
    0.55
    絶対に
    0.52
     لأن
    0.51
     因為
    0.48
     Çünkü
    0.48
    因為
    0.47
     pretože
    0.45
    দিগকে
    0.44
     کیونکہ
    0.44
     بالکل
    0.44
    Activations Density 0.011%

    No Known Activations