© 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. 104445
    Prev
    Next
    INDEX
    Explanations

    its matching; whenever; tickets; enquiries; , FL; they have; in Virginia; much Love; malware version

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

    topics and descriptions

    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
     is
    0.48
     rhizosphere
    0.47
     in
    0.46
     your
    0.45
     a
    0.44
     kim
    0.44
     perpendicular
    0.43
    u
    0.43
     domest
    0.43
    acch
    0.43
    POSITIVE LOGITS
    放弃
    0.55
    忏
    0.50
    。”
    0.48
    zaXRvcn
    0.48
    惭
    0.47
     فلسطینی
    0.47
     약간
    0.47
    halloween
    0.47
    راهيم
    0.47
    损伤
    0.46
    Activations Density 0.000%

    No Known Activations