© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10907
    Prev
    Next
    INDEX
    Explanations

    occupations and their activities

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

    transformers, players, developers

    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_40_width_16k_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
    ㈤
    0.38
     personality
    0.38
    祢
    0.38
    omét
    0.37
    يانة
    0.36
     DHT
    0.36
    达
    0.36
     Arora
    0.36
     Santorini
    0.35
    奇
    0.35
    POSITIVE LOGITS
    hip
    0.51
    hips
    0.51
    pace
    0.46
     rejoice
    0.46
    宁
    0.46
     क्लब
    0.45
     CLUB
    0.45
     realizaron
    0.45
    rsquo
    0.44
     अड्डा
    0.44
    Activations Density 0.261%

    No Known Activations