© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13131
    Prev
    Next
    INDEX
    Explanations

    machine services, factor configuration, surveillance

    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
     on
    -1.89
     to
    -1.80
    </h2>
    -1.63
     it
    -1.43
     (
    -1.38
    </sup>
    -1.38
     this
    -1.35
    </h1>
    -1.34
     that
    -1.32
    我也
    -1.26
    POSITIVE LOGITS
     is
    1.45
     our
    1.40
     bedrijven
    1.38
     μας
    1.38
     χωρίς
    1.37
     verdieping
    1.37
     gibts
    1.34
     récemment
    1.33
     telefoon
    1.31
    жнее
    1.31
    Activations Density 0.163%

    No Known Activations