© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 6893
    Prev
    Next
    INDEX
    Explanations

    simple and easy to use

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

    simple explanations or calculations

    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_53_width_65k_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
     barges
    0.43
    ݢ
    0.38
     barge
    0.38
     fabb
    0.37
    ヮ
    0.37
    ファー
    0.37
     ANON
    0.37
     বাঙ
    0.37
     ANAL
    0.36
     LANC
    0.36
    POSITIVE LOGITS
     ቢ
    0.41
    umlah
    0.40
     involvement
    0.39
    ift
    0.38
    शा
    0.37
     overall
    0.37
     placeholders
    0.37
    ikul
    0.36
     interest
    0.36
    ifai
    0.36
    Activations Density 0.000%

    No Known Activations