© 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. 101442
    Prev
    Next
    INDEX
    Explanations

    following articles or descriptive words

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

    attention, maintenance, research, beam, endorsing

    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
     leurs
    0.45
     `<=
    0.43
     qu
    0.43
     celui
    0.42
     televisi
    0.42
     emir
    0.41
     njen
    0.41
     beaucoup
    0.41
     dont
    0.40
    才有
    0.40
    POSITIVE LOGITS
     означает
    0.50
    掇
    0.48
    ator
    0.46
    मूल
    0.45
    峽
    0.44
     tarko
    0.44
    ī
    0.43
    ادة
    0.43
    طور
    0.42
     ވަ
    0.42
    Activations Density 0.000%

    No Known Activations