© 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. 70701
    Prev
    Next
    INDEX
    Explanations

    who is the

    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
     sposob
    -1.52
     something
    -1.37
     configuration
    -1.37
     dikembangkan
    -1.35
    Different
    -1.35
     TÉCNICA
    -1.35
     characteristic
    -1.32
    ၢ
    -1.28
     achieved
    -1.27
     structure
    -1.23
    POSITIVE LOGITS
     этих
    1.24
    =−
    1.20
    >();
    1.20
    ancing
    1.17
    ))=
    1.16
    zsche
    1.16
     ваших
    1.14
    </h2>
    1.13
     −
    1.11
     *.
    1.11
    Activations Density 0.010%

    No Known Activations