© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 98339
    Prev
    Next
    INDEX
    Explanations

    trains and buses

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

    copying lyricsapproaching friendlysilicon valley technologycredible astronomer

    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
     embers
    0.50
     announce
    0.47
    ҳ
    0.46
     ஓர
    0.46
     announcements
    0.46
    residuals
    0.46
     anunciar
    0.46
     parishioners
    0.45
     ump
    0.45
     incrementally
    0.45
    POSITIVE LOGITS
    鼠
    0.52
    ський
    0.51
     piscine
    0.49
    UTION
    0.49
     زي
    0.49
    HE
    0.46
     государственный
    0.46
    瑞士
    0.46
    UB
    0.45
     صع
    0.44
    Activations Density 0.000%

    No Known Activations