© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128580
    Prev
    Next
    INDEX
    Explanations

    try block or async operations

    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
     Perſ
    -1.38
    ℉
    -1.28
    ↵↵
    -1.27
     whoſe
    -1.24
     lèvres
    -1.24
    )
    -1.23
     
    -1.20
     kuan
    -1.19
     iko
    -1.19
     EVEN
    -1.18
    POSITIVE LOGITS
     případě
    1.45
     there
    1.40
    There
    1.39
     should
    1.37
     at
    1.37
     with
    1.35
     경우
    1.35
     There
    1.34
     jsme
    1.28
    gás
    1.26
    Activations Density 0.003%

    No Known Activations