© 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. 60531
    Prev
    Next
    INDEX
    Explanations

    ignoring or highlighting selections

    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
    <unused47>
    0.52
     só
    0.49
    みの
    0.47
     Dương
    0.47
     dhinak
    0.46
     Người
    0.45
    ]".
    0.45
     Ảnh
    0.45
     ভাষার
    0.45
     لال
    0.44
    POSITIVE LOGITS
    ปี
    0.46
    LO
    0.44
    opaedia
    0.44
    program
    0.41
    怔
    0.41
    archiwizowane
    0.41
     microarray
    0.39
     of
    0.39
     group
    0.39
    我想
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.