© 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. 101328
    Prev
    Next
    INDEX
    Explanations

    places like Clemson, Hershey, Sonoma

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

    the names of geographic locations or venue/place proper nouns.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    
    -2.61
    躂
    -2.52
    鶿
    -2.45
    焢
    -2.42
    ⸨
    -2.36
    櫺
    -2.31
    翃
    -2.30
    ឣ
    -2.22
    ꜆
    -2.22
     البته
    -2.22
    POSITIVE LOGITS
    怍
    2.48
    鹚
    2.34
     has
    2.14
    带宽
    2.13
     says
    2.13
    龊
    2.13
     новая
    2.09
    useppe
    2.08
    &#
    2.06
     was
    2.05
    Activations Density 0.006%

    No Known Activations