© 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. 231810
    Prev
    Next
    INDEX
    Explanations

    due date and department

    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
     headphone
    0.45
     Jing
    0.42
     than
    0.42
    _
    0.41
     spout
    0.40
     href
    0.40
     booze
    0.39
     luyện
    0.39
     Email
    0.38
    腆
    0.38
    POSITIVE LOGITS
    cké
    0.50
    కో
    0.47
     établ
    0.47
    ጶ
    0.46
    સર
    0.46
    టికి
    0.46
    Duke
    0.45
    촬
    0.45
    fordern
    0.45
    clé
    0.45
    Activations Density 0.001%

    No Known Activations