© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 200961
    Prev
    Next
    INDEX
    Explanations

    controller or third party

    np_acts-logits-general · gemini-2.5-flash-lite

    art nouveau, entity, revolution, pearl

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =>
    0.55
     automatisch
    0.52
     пів
    0.48
     s
    0.48
     Commentary
    0.48
    OD
    0.47
     putih
    0.47
    Compare
    0.46
    <0xD2>
    0.45
     বলেছে
    0.45
    POSITIVE LOGITS
    codon
    0.55
    stituting
    0.50
    representing
    0.48
    ீரி
    0.46
    fourths
    0.45
    უქ
    0.44
     promulgating
    0.44
    ビング
    0.44
    퓸
    0.43
    expressing
    0.42
    Activations Density 0.000%

    No Known Activations