© 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. 10-GEMMASCOPE-RES-131K
    7. 103223
    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-27b-pt-res/layer_10/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
    acamole
    -1.41
     gudang
    -1.40
     yoktur
    -1.34
     senjata
    -1.30
     these
    -1.27
    use
    -1.23
    Джере
    -1.20
     they
    -1.19
     cabang
    -1.18
     use
    -1.16
    POSITIVE LOGITS
     włosów
    1.35
    ഃ
    1.33
    ():
    1.25
    [])
    1.23
    rän
    1.16
     sabem
    1.13
     (
    1.12
     acces
    1.10
    }
    1.08
     Cualquier
    1.05
    Activations Density 0.134%

    No Known Activations