© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13911
    Prev
    Next
    INDEX
    Explanations

    Physical Review Letters

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

    nonverbal cues, application, exam, workout, innovation

    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_16k_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
     Storage
    0.49
     storage
    0.46
    ศาสตร์
    0.46
     بسیاری
    0.46
    മല്ല
    0.46
     ث
    0.44
    数の
    0.44
     tramp
    0.44
     toutes
    0.44
     politique
    0.44
    POSITIVE LOGITS
     nedeni
    0.47
     dedo
    0.45
    ǯ
    0.45
    rhein
    0.45
    ilot
    0.44
     настолько
    0.43
    bleed
    0.43
    жи
    0.43
    ensi
    0.43
     dedi
    0.43
    Activations Density 0.012%

    No Known Activations