© 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. 34-GEMMASCOPE-RES-131K
    7. 118531
    Prev
    Next
    INDEX
    Explanations

    according to, by

    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_34/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
    orphaned
    -0.88
     sapere
    -0.84
    .";
    -0.76
    它们的
    -0.75
     Gameplay
    -0.71
     bitters
    -0.70
    ロナ
    -0.69
    indul
    -0.69
    ""}
    -0.69
     ");
    -0.68
    POSITIVE LOGITS
    comic
    0.99
     prev
    0.91
    θη
    0.89
     Comic
    0.89
     comic
    0.89
    prev
    0.89
    теше
    0.84
     Chamber
    0.81
    Comic
    0.79
    階の
    0.78
    Activations Density 0.012%

    No Known Activations