© 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. 29083
    Prev
    Next
    INDEX
    Explanations

    words like pardi, shyness, enantiomorphous

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

    formal language and specific concepts

    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
    「
    0.56
     「
    0.54
    ($
    0.52
    ("
    0.51
    （
    0.50
    の
    0.50
    す
    0.48
    (
    0.48
     (
    0.47
    (<
    0.47
    POSITIVE LOGITS
     এইরূপে
    0.44
    ખ્યા
    0.44
    ুব্ধ
    0.43
    ত্যাশিত
    0.43
     parish
    0.42
    <unused2149>
    0.42
    র্ষি
    0.42
    ục
    0.41
     bituminous
    0.41
     lưu
    0.41
    Activations Density 0.001%

    No Known Activations