© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 235
    Prev
    Next
    INDEX
    Explanations

    films with subtitles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    yaml
    0.76
    校验
    0.73
    abelian
    0.72
    textvariable
    0.72
    covariance
    0.69
     inactivation
    0.69
    苯
    0.69
    潍
    0.68
    ylsulfanyl
    0.68
     液
    0.66
    POSITIVE LOGITS
     filmmakers
    3.28
     filmmaking
    3.21
     film
    3.19
     filming
    3.02
     filmmaker
    3.01
     films
    2.98
     Film
    2.98
     screenwriter
    2.95
     movie
    2.89
    film
    2.87
    Activations Density 2.614%

    No Known Activations