© 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. 100337
    Prev
    Next
    INDEX
    Explanations

    was appointed/elected/joined

    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
     сьогодні
    -1.51
    𖣔
    -1.51
     négoci
    -1.47
     eventuell
    -1.41
    lepší
    -1.41
    〬
    -1.41
    красный
    -1.41
     laisser
    -1.40
    Ꮚ
    -1.39
    ཿ
    -1.38
    POSITIVE LOGITS
     when
    2.05
     and
    1.80
    ;
    1.74
     about
    1.65
     is
    1.58
     during
    1.57
     in
    1.55
     by
    1.50
    w
    1.46
     before
    1.42
    Activations Density 0.127%

    No Known Activations