© 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. 154608
    Prev
    Next
    INDEX
    Explanations

    data from various languages

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

    describing things in detail

    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
    ation
    0.51
    ies
    0.50
    in
    0.48
    um
    0.48
    u
    0.48
    ophobia
    0.47
    s
    0.47
    im
    0.46
    ix
    0.46
     excessive
    0.46
    POSITIVE LOGITS
     পেছনে
    0.51
    стрее
    0.49
     данни
    0.47
    Yep
    0.46
     nummer
    0.45
     gegevens
    0.45
    數據
    0.45
     минера
    0.44
    ้อมูล
    0.44
    データ
    0.44
    Activations Density 0.002%

    No Known Activations