© 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. 47573
    Prev
    Next
    INDEX
    Explanations

    code syntax elements

    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
    >
    -1.27
     vna
    -1.24
     vidi
    -1.23
     and
    -1.16
     >
    -1.16
     our
    -1.15
    »:
    -1.14
     bascul
    -1.13
     zodia
    -1.12
    ایای
    -1.10
    POSITIVE LOGITS
    DebuggerStep
    1.27
     you
    1.18
     außerdem
    1.15
    ovala
    1.13
    genheiten
    1.12
     aplikacji
    1.12
    skapet
    1.12
    最多的
    1.11
     czarny
    1.10
     niebieski
    1.09
    Activations Density 0.016%

    No Known Activations