© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14826
    Prev
    Next
    INDEX
    Explanations

    urban place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     your
    -1.18
    場所で
    -1.16
     ogrodow
    -1.13
     zwanzig
    -1.07
    řízen
    -1.05
    場所に
    -1.04
    Джере
    -1.02
    んです
    -1.02
     miejscowości
    -1.02
    AsNil
    -1.00
    POSITIVE LOGITS
     downtown
    1.65
     Downtown
    1.43
    Downtown
    1.30
    downtown
    1.16
     CBD
    1.13
     городской
    1.13
     موبایل
    1.00
     здание
    0.99
     intractable
    0.99
    Opis
    0.97
    Activations Density 0.117%

    No Known Activations