© 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. 180983
    Prev
    Next
    INDEX
    Explanations

    lecture

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

    educational lectures, physiology

    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
     pouvaient
    0.51
     pc
    0.49
     potrebbero
    0.47
     pourraient
    0.46
     could
    0.46
     インド
    0.46
     ਦ
    0.46
     调用
    0.45
     送
    0.45
     打
    0.44
    POSITIVE LOGITS
     Lecture
    0.50
    Lecture
    0.50
    ир
    0.48
    lecture
    0.46
     Schwerpunkt
    0.44
    gtrsim
    0.44
    の変化
    0.44
    lesssim
    0.43
    න්ධ
    0.43
     محاضرت
    0.43
    Activations Density 0.001%

    No Known Activations