© 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. 59555
    Prev
    Next
    INDEX
    Explanations

    Bootstrap UI components

    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
     différentes
    -1.23
     DIFFERENT
    -1.19
     producten
    -1.19
    тилась
    -1.18
     produkter
    -1.17
     semej
    -1.16
     différents
    -1.16
    iconque
    -1.15
     theſe
    -1.13
    égal
    -1.13
    POSITIVE LOGITS
     in
    1.43
    我们在
    1.26
    Noe
    1.13
    ladolid
    1.10
    CORO
    1.08
     with
    1.05
    ַּ
    1.03
     merusak
    1.02
    Beschrijving
    1.02
    Fonto
    1.02
    Activations Density 0.054%

    No Known Activations