© 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. 145695
    Prev
    Next
    INDEX
    Explanations

    orand.approx;av",mean

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

    economy, absorbing, regulation

    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
    fehler
    0.50
    སྐ
    0.47
    já
    0.46
    j
    0.46
     Dzięki
    0.46
    Grazie
    0.45
    签
    0.45
    年来
    0.45
    fälle
    0.45
     QTreeWidgetItem
    0.45
    POSITIVE LOGITS
    Cal
    0.47
     Cal
    0.45
     экономи
    0.43
    ould
    0.42
     мульти
    0.42
    multif
    0.42
     لاست
    0.41
     предпо
    0.41
     Gresham
    0.40
     Prou
    0.40
    Activations Density 0.002%

    No Known Activations