© 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. 107351
    Prev
    Next
    INDEX
    Explanations

    technical terms and future concepts

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

    seraphina, argonaut, more, values, do you

    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
     Unlock
    0.45
     chocolate
    0.44
     ۵
    0.41
     CAD
    0.41
    ektiv
    0.40
    에서도
    0.40
    unlock
    0.40
     waste
    0.39
     Bloc
    0.39
     Complex
    0.39
    POSITIVE LOGITS
    Mât
    0.52
    custList
    0.52
    莒
    0.50
    虑
    0.49
    otipo
    0.48
    道理
    0.48
    ěstí
    0.48
    ليل
    0.48
     መስ
    0.47
    سة
    0.47
    Activations Density 0.000%

    No Known Activations