© 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. 34-GEMMASCOPE-RES-131K
    7. 117568
    Prev
    Next
    INDEX
    Explanations

    first of time periods

    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
     gedurende
    -1.09
    筊
    -1.05
     Laufe
    -0.97
    æng
    -0.94
    čem
    -0.93
     görünt
    -0.93
     протягом
    -0.92
     gethan
    -0.90
     peně
    -0.88
    doria
    -0.87
    POSITIVE LOGITS
     of
    4.34
    ของ
    1.65
     της
    1.13
     into
    1.07
     что
    0.97
     của
    0.97
     такого
    0.89
     нового
    0.88
     τῆς
    0.87
     after
    0.85
    Activations Density 0.035%

    No Known Activations