© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 31
    Prev
    Next
    INDEX
    Explanations

    fake, mock, simulated entities

    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
     rağmen
    -1.16
    Fully
    -1.16
    veien
    -1.15
    新しい
    -1.14
     reducido
    -1.14
     rafra
    -1.13
     konkret
    -1.13
     včetně
    -1.12
    }{\
    -1.10
     ktorí
    -1.09
    POSITIVE LOGITS
     because
    1.59
     for
    1.54
     a
    1.47
     by
    1.42
     at
    1.28
     just
    1.27
     about
    1.26
     since
    1.26
     an
    1.19
     three
    1.15
    Activations Density 0.103%

    No Known Activations