© 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. 232
    Prev
    Next
    INDEX
    Explanations

    you and me

    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
     interdiscipl
    0.61
     eloquently
    0.57
     irregularly
    0.55
    ⵅ
    0.54
     monstros
    0.54
     vaguely
    0.54
    㣩
    0.54
     Roughly
    0.54
     schlecht
    0.54
     puiss
    0.53
    POSITIVE LOGITS
    yn
    0.56
    aram
    0.53
    rec
    0.51
    e
    0.50
    pinimg
    0.50
    ց
    0.49
    rn
    0.49
    red
    0.48
    ala
    0.48
    il
    0.48
    Activations Density 0.724%

    No Known Activations