© 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. 15290
    Prev
    Next
    INDEX
    Explanations

    materials and methods Canyon Smith

    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
    鼉
    -1.84
     secteurs
    -1.65
    为何
    -1.64
    扨
    -1.61
     cœurs
    -1.55
     capacités
    -1.55
     ด้วย
    -1.47
    祧
    -1.46
    簓
    -1.46
     acte
    -1.44
    POSITIVE LOGITS
    2
    3.14
     nawet
    1.84
    7
    1.79
    4
    1.75
    as
    1.73
    6
    1.66
     of
    1.63
    5
    1.63
    3
    1.59
     bahkan
    1.53
    Activations Density 0.068%

    No Known Activations