© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1403
    Prev
    Next
    INDEX
    Explanations

    grouping

    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
    ckte
    0.87
    鏻
    0.84
    PLICATIONS
    0.79
    DLJ
    0.78
    ђе
    0.77
    かります
    0.74
    GTG
    0.74
    quées
    0.73
    ၷ
    0.72
    chlorate
    0.71
    POSITIVE LOGITS
    ers
    1.64
    able
    1.61
    ingly
    1.55
    ive
    1.50
    ed
    1.43
    edly
    1.42
    ative
    1.42
    er
    1.40
    ing
    1.37
    ous
    1.37
    Activations Density 0.737%

    No Known Activations