© 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. 111297
    Prev
    Next
    INDEX
    Explanations

    scope of contents

    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
     dévelo
    -2.14
     Including
    -2.13
     Ако
    -2.11
    祎
    -1.98
     Could
    -1.98
    ﺓ
    -1.95
     verschil
    -1.95
    自己是
    -1.87
     preservar
    -1.84
    рії
    -1.83
    POSITIVE LOGITS
    ();
    2.33
    ed
    2.27
    𐄙
    2.19
    ᐕ
    2.06
     mocking
    2.05
     другое
    2.00
     banyo
    2.00
     scope
    2.00
     pero
    1.98
     minim
    1.98
    Activations Density 0.015%

    No Known Activations