© 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. 66273
    Prev
    Next
    INDEX
    Explanations

    town and city 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
     testar
    -1.18
    baik
    -1.12
     ')
    -1.10
    様です
    -1.09
    ardu
    -1.09
    犢
    -1.06
    bando
    -1.05
    🚮
    -1.05
     comprobar
    -1.05
     города
    -1.05
    POSITIVE LOGITS
    two
    1.39
     o
    1.34
    もある
    1.30
     them
    1.18
    tra
    1.13
    four
    1.10
    mazioni
    1.10
     solicitó
    1.09
    stone
    1.09
    fiés
    1.08
    Activations Density 0.129%

    No Known Activations