© 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. 175058
    Prev
    Next
    INDEX
    Explanations

    impossible that, increasingly recognized

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

    contribute to

    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
    ojen
    0.51
     Slovak
    0.48
     Yugoslav
    0.46
     '
    0.46
     Fällen
    0.45
     sosten
    0.44
     Sierra
    0.44
     Alkaline
    0.43
     adheres
    0.43
     frivolous
    0.43
    POSITIVE LOGITS
    ຢູ່ໃນ
    0.52
    
    0.50
    льно
    0.50
    を送
    0.48
    
    0.48
    扂
    0.48
    
    0.47
    ｶ
    0.47
    샨
    0.46
    ꧁
    0.46
    Activations Density 0.000%

    No Known Activations