© 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. 159386
    Prev
    Next
    INDEX
    Explanations

    paise per, can be, as a

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

    communication protocols

    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
     whence
    0.49
     ;
    0.47
    condition
    0.44
     обл
    0.43
    vý
    0.42
    ָ
    0.41
    preferably
    0.41
    towards
    0.41
    although
    0.41
    憬
    0.41
    POSITIVE LOGITS
     wichtigsten
    0.45
     собрать
    0.45
     values
    0.44
     licensure
    0.43
     feme
    0.43
     primary
    0.43
     terbaru
    0.43
     patrocin
    0.43
     negara
    0.42
     pekerjaan
    0.42
    Activations Density 0.001%

    No Known Activations