© 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. 73608
    Prev
    Next
    INDEX
    Explanations

    transitional home features

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

    ranking and comparison

    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
    博客
    0.46
     Ejec
    0.44
     Fiscal
    0.43
     Promises
    0.43
    嬗
    0.43
     ব্লগ
    0.42
     রওনা
    0.42
     Katalog
    0.42
     Fant
    0.42
    భర
    0.42
    POSITIVE LOGITS
    糰
    0.45
     inappropriately
    0.44
    による
    0.43
    வ்
    0.42
     précisément
    0.42
     нега
    0.41
    陀
    0.41
    士
    0.40
     wrongly
    0.40
    дку
    0.40
    Activations Density 0.013%

    No Known Activations