© 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. 43
    Prev
    Next
    INDEX
    Explanations

    the script, code, function

    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
     합니다
    0.71
     เช่น
    0.70
    입니다
    0.68
    합니다
    0.65
    circa
    0.61
    Shortly
    0.60
     precludes
    0.58
    ~!
    0.58
     ㅋㅋ
    0.58
    presumably
    0.57
    POSITIVE LOGITS
     whole
    1.02
     aforesaid
    0.88
     same
    0.85
     mentioned
    0.84
     following
    0.74
     most
    0.73
     entire
    0.72
     latter
    0.72
     above
    0.71
     aforementioned
    0.71
    Activations Density 1.622%

    No Known Activations