© 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. 41838
    Prev
    Next
    INDEX
    Explanations

    're, 'cause, 'course

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

    definition lists and code examples

    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
     नियोजन
    0.48
    väl
    0.47
     आकलन
    0.44
    मेट्री
    0.43
     terapia
    0.43
     सकारात्मक
    0.42
    蟻
    0.42
     algorit
    0.41
    धारक
    0.41
    存档备份
    0.41
    POSITIVE LOGITS
    .[
    0.51
    Complete
    0.46
     ][
    0.44
     whose
    0.44
    Desc
    0.44
    8
    0.44
     impeccable
    0.42
    Neder
    0.41
    Ἔ
    0.41
    ✵
    0.40
    Activations Density 0.000%

    No Known Activations