© 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. 100765
    Prev
    Next
    INDEX
    Explanations

    leader of

    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
     '
    -1.80
    甞
    -1.77
    e
    -1.64
    蠅
    -1.58
    ᳝
    -1.51
    てて
    -1.48
    🧌
    -1.46
    櫚
    -1.45
    oks
    -1.44
    ;'
    -1.43
    POSITIVE LOGITS
     ‘‘
    1.66
    "};
    1.65
     Their
    1.65
     of
    1.57
     are
    1.52
    ときの
    1.48
     Consequently
    1.48
     leaders
    1.47
     Где
    1.42
    领导
    1.41
    Activations Density 0.018%

    No Known Activations