© 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. 844
    Prev
    Next
    INDEX
    Explanations

    system names or toolkits

    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
    所属
    0.57
    _
    0.55
    ice
    0.52
    rop
    0.51
    ai
    0.51
     В
    0.50
    ͜
    0.50
    depend
    0.49
     С
    0.49
     yours
    0.48
    POSITIVE LOGITS
     Initiative
    1.21
     Toolkit
    1.19
     toolkit
    1.14
     guidebook
    1.08
     initiative
    1.08
     handbook
    1.06
     Handbook
    1.01
     Consortium
    0.99
     Symposium
    0.98
     symposium
    0.95
    Activations Density 1.062%

    No Known Activations