© 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. 86274
    Prev
    Next
    INDEX
    Explanations

    Liberia, Benin, Harlem

    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
    2
    -2.88
    
    -2.48
    じゃあ
    -2.48
    榖
    -2.42
     yapılır
    -2.38
    lossians
    -2.30
    應該是
    -2.28
    celotti
    -2.27
    medriver
    -2.23
     blemish
    -2.23
    POSITIVE LOGITS
    炱
    2.58
     evidenced
    2.56
    鹛
    2.17
    }$
    2.08
     但
    2.05
    ce
    2.03
    D
    2.02
     troubles
    1.98
    銲
    1.95
     ism
    1.94
    Activations Density 0.007%

    No Known Activations