© 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. 162586
    Prev
    Next
    INDEX
    Explanations

    art conservation

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

    keywords and technical terms

    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
     nvp
    0.56
     ।,
    0.56
     événements
    0.55
    르는
    0.51
     convertido
    0.51
    프
    0.50
     ।
    0.49
    臨界
    0.48
    ると
    0.48
     ৩৫
    0.48
    POSITIVE LOGITS
    h
    0.58
    ada
    0.56
    ö
    0.51
    authorization
    0.50
    ed
    0.49
    d
    0.49
    ian
    0.48
    authentication
    0.48
    anti
    0.48
    ah
    0.47
    Activations Density 0.000%

    No Known Activations