© 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. 525
    Prev
    Next
    INDEX
    Explanations

    describing complex or specific capabilities

    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
     最後
    0.51
     тоже
    0.50
     然後
    0.49
    Its
    0.47
     Hälfte
    0.46
     Вообще
    0.46
    ☹
    0.46
     (?)
    0.46
     なお
    0.46
    Thats
    0.46
    POSITIVE LOGITS
     innovative
    1.17
     various
    1.12
     sophisticated
    1.10
     numerous
    1.06
     unique
    1.04
     diverse
    1.00
     customized
    1.00
     intricate
    1.00
     specialized
    0.99
     different
    0.96
    Activations Density 9.335%

    No Known Activations