© 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. 102494
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and expressions

    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
     sirop
    -1.15
    āya
    -1.13
     reaf
    -1.12
     fenomen
    -1.11
     issus
    -1.09
     servis
    -1.07
     МЕ
    -1.07
     instru
    -1.07
     ЛИ
    -1.05
    Suisse
    -1.05
    POSITIVE LOGITS
    anguardia
    1.30
     bezpośrednio
    1.28
     what
    1.26
     faster
    1.25
     mocno
    1.25
     ohnehin
    1.23
     we
    1.20
     solchen
    1.18
     erweiter
    1.17
     where
    1.16
    Activations Density 0.089%

    No Known Activations