© 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. 66210
    Prev
    Next
    INDEX
    Explanations

    Bank of [Place/Institution Name]

    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
     However
    -2.52
     Such
    -2.28
     Though
    -2.09
    诸多
    -2.06
     That
    -2.06
     Other
    -2.02
    section
    -1.98
     Recently
    -1.94
    on
    -1.93
     Earlier
    -1.91
    POSITIVE LOGITS
    殽
    2.06
    읗
    2.03
    鈰
    2.03
     סרט
    2.00
    
    1.96
     всѣ
    1.95
    Ꮂ
    1.95
    genodigd
    1.94
    heiten
    1.94
    ㈰
    1.89
    Activations Density 0.007%

    No Known Activations