© 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. 137418
    Prev
    Next
    INDEX
    Explanations

    you sign

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

    SEO, Engineer, Report

    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
     festge
    0.47
     compositions
    0.44
     processi
    0.43
     Alban
    0.42
    ствах
    0.41
     geli
    0.41
     fui
    0.41
    푸
    0.41
    дите
    0.41
     voler
    0.41
    POSITIVE LOGITS
     \
    0.51
    aw
    0.51
    Municipio
    0.50
    ল
    0.50
    bedroom
    0.49
    ciudad
    0.49
     বাঁচ
    0.46
    center
    0.46
    Though
    0.46
    聯
    0.46
    Activations Density 0.001%

    No Known Activations