© 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. 164
    Prev
    Next
    INDEX
    Explanations

    Miss or pragmatic leader

    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
     센터
    0.42
     인천
    0.39
     REGULATIONS
    0.38
     Statewide
    0.37
    artment
    0.37
    省级
    0.37
     수원
    0.36
    ⛩
    0.35
     ইউএন
    0.35
    مركز
    0.35
    POSITIVE LOGITS
     Charles
    1.08
     Robert
    1.05
     William
    1.04
     George
    1.03
     Henry
    1.02
     Edward
    1.01
     Jacques
    1.00
     Walter
    1.00
     Joseph
    0.99
     Richard
    0.99
    Activations Density 3.768%

    No Known Activations