© 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. 14
    Prev
    Next
    INDEX
    Explanations

    stating or mentioning information

    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
     자동으로
    0.71
     endlich
    0.70
    libat
    0.68
    ajemy
    0.67
     производится
    0.67
    тории
    0.67
    ޢ
    0.65
    順番
    0.65
     funziona
    0.65
     eignet
    0.64
    POSITIVE LOGITS
     said
    3.38
     mengatakan
    3.21
     saying
    3.17
     stated
    3.13
     says
    3.08
     stating
    2.94
    said
    2.90
     say
    2.86
    说
    2.69
     remarked
    2.69
    Activations Density 3.587%

    No Known Activations