© 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. 557
    Prev
    Next
    INDEX
    Explanations

    city names

    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
     whole
    0.49
     manage
    0.46
     dwarf
    0.44
     pre
    0.44
    0.44
     starting
    0.43
     dwar
    0.42
     n
    0.42
     trad
    0.42
     grunt
    0.42
    POSITIVE LOGITS
    ópolis
    0.85
    adolid
    0.78
    sville
    0.78
    hamton
    0.77
    ignano
    0.76
    ândia
    0.73
    zków
    0.73
    ersburg
    0.73
    州市
    0.72
    derabad
    0.70
    Activations Density 0.713%

    No Known Activations