© 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. 765
    Prev
    Next
    INDEX
    Explanations

    quantifying years and figures

    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
    ει
    0.68
    örü
    0.68
    ँग
    0.67
    तरे
    0.65
    řej
    0.63
    estellt
    0.62
    ायतों
    0.62
     '\\;'
    0.61
    idikan
    0.61
    folg
    0.61
    POSITIVE LOGITS
    hrs
    0.72
     Minutes
    0.68
     mins
    0.67
     hrs
    0.67
    5
    0.66
    px
    0.65
    ,-
    0.65
     minutes
    0.65
    %,
    0.64
    minutes
    0.62
    Activations Density 0.137%

    No Known Activations