© 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. 111299
    Prev
    Next
    INDEX
    Explanations

    San Francisco

    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
     neun
    -1.60
    ccoli
    -1.60
    les
    -1.52
    *
    -1.44
     deberán
    -1.42
                
    -1.39
     силы
    -1.37
    して下さい
    -1.35
    in
    -1.34
    龉
    -1.33
    POSITIVE LOGITS
     veda
    1.78
     pantal
    1.70
     fusil
    1.66
     gitt
    1.51
     bronz
    1.50
     eſſ
    1.44
     bateau
    1.43
    OLOGY
    1.43
     puni
    1.42
     chaises
    1.42
    Activations Density 0.044%

    No Known Activations