© 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. 68299
    Prev
    Next
    INDEX
    Explanations

    names like Natasha, Britt, Vijay

    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
     was
    -3.39
     of
    -2.78
     Then
    -2.67
    D
    -2.64
    isation
    -2.58
     However
    -2.47
     iedere
    -2.47
     Similarly
    -2.45
     Until
    -2.45
     Again
    -2.39
    POSITIVE LOGITS
    鬭
    2.52
    擁有
    2.52
    Harga
    2.42
    بحث
    2.39
     vorsichtig
    2.38
    Tempat
    2.36
     知道
    2.33
    紲
    2.31
     petites
    2.31
     the
    2.30
    Activations Density 0.020%

    No Known Activations