© 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. 8739
    Prev
    Next
    INDEX
    Explanations

    cities, corporations, nations

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

    nations, companies, cities

    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
     następnie
    0.46
    その後
    0.46
     לאחר
    0.44
     Campylobacter
    0.43
     Vamp
    0.43
     Penelope
    0.41
     Física
    0.41
    饲
    0.41
     பிறகு
    0.41
     násled
    0.41
    POSITIVE LOGITS
     cities
    0.73
     COMPANIES
    0.71
     legislatures
    0.66
     republics
    0.64
     corporations
    0.64
     ciudades
    0.64
     nations
    0.63
     municipalities
    0.61
     міста
    0.61
     gobiernos
    0.60
    Activations Density 0.000%

    No Known Activations