© 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. 113011
    Prev
    Next
    INDEX
    Explanations

    not by a long shot

    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
    }$.
    -1.45
     contempla
    -1.44
     responsabili
    -1.40
    艫
    -1.39
    。"
    -1.39
    ！"
    -1.37
    gebnissen
    -1.35
     contextLoads
    -1.34
     aérea
    -1.34
     though
    -1.32
    POSITIVE LOGITS
    {
    1.77
     also
    1.57
     Also
    1.27
    zydent
    1.26
    СЫ
    1.23
     a
    1.23
     on
    1.23
    ζ
    1.23
     branche
    1.22
    andte
    1.20
    Activations Density 0.007%

    No Known Activations