© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19294
    Prev
    Next
    INDEX
    Explanations

    county names

    np_acts-logits-general · gemini-2.5-flash-lite

    place names followed by county

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    cular
    0.42
    õ
    0.42
    శ్వ
    0.42
     Certains
    0.41
     Osm
    0.41
    rance
    0.40
     Define
    0.40
     Determine
    0.40
     Schä
    0.40
     Subset
    0.40
    POSITIVE LOGITS
     county
    0.69
     County
    0.64
     counties
    0.57
    County
    0.57
    county
    0.55
    县
    0.54
     COUNTY
    0.51
    縣
    0.50
     Counties
    0.47
    県
    0.42
    Activations Density 0.082%

    No Known Activations