© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 2001
    Prev
    Next
    INDEX
    Explanations

    photographs and photography

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     CEST
    1.33
    ɾ
    1.33
    พน
    1.30
     TypeScript
    1.29
    oxicity
    1.29
    ابل
    1.28
    discord
    1.27
     оюн
    1.26
     websocket
    1.25
    ḿ
    1.24
    POSITIVE LOGITS
     photograph
    3.18
     photographs
    3.13
     photos
    2.98
     photographing
    2.97
     Photos
    2.95
     Photographs
    2.93
     Photography
    2.93
     photographers
    2.92
     photographic
    2.90
     Photographer
    2.89
    Activations Density 1.553%

    No Known Activations