© 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. 14746
    Prev
    Next
    INDEX
    Explanations

    his interviewees

    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
     to
    -1.27
     fatale
    -1.25
     herbes
    -1.24
     arme
    -1.23
    Popular
    -1.23
    ⢌
    -1.22
    ಎ
    -1.21
     parfums
    -1.20
     rasch
    -1.17
     طراحی
    -1.15
    POSITIVE LOGITS
     there
    2.00
     maravillosas
    1.80
     probablemente
    1.77
     you
    1.76
     that
    1.74
     maybe
    1.70
     impresionantes
    1.68
     najdete
    1.66
     obsahuje
    1.60
     posibles
    1.59
    Activations Density 0.010%

    No Known Activations