© 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. 187645
    Prev
    Next
    INDEX
    Explanations

    numbers and amounts

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

    open weights implications

    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
     Tulane
    0.44
    が登場
    0.43
     quantitatively
    0.42
    🎁
    0.42
     pote
    0.42
     wronged
    0.41
    aughters
    0.41
    SHALL
    0.41
    賭
    0.40
    čili
    0.40
    POSITIVE LOGITS
     Ку
    0.51
     Эти
    0.51
     Bağ
    0.51
    لای
    0.50
     Học
    0.49
     Бай
    0.48
     Cámara
    0.48
    ل
    0.47
     Gén
    0.47
     Org
    0.46
    Activations Density 0.000%

    No Known Activations