© 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
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6995
    Prev
    Next
    INDEX
    Explanations

    profession, sport, craft, genre

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

    the specific field or concept

    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
     কথায়
    0.39
    諸
    0.39
     ไหน
    0.38
    今天要
    0.37
    明け
    0.36
    〖
    0.36
    aggia
    0.36
    诸
    0.36
    ^^
    0.35
    ^^^^
    0.35
    POSITIVE LOGITS
     genre
    1.39
     profession
    1.33
     craft
    1.33
    genre
    1.21
     profesión
    1.17
     жан
    1.15
     професси
    1.05
     métier
    1.05
     sport
    1.05
     discipline
    1.05
    Activations Density 0.148%

    No Known Activations