© 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. 210541
    Prev
    Next
    INDEX
    Explanations

    users view counts

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

    specific technical or foreign words

    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
     宋
    0.50
    網站
    0.50
    üsü
    0.49
    rasi
    0.49
    ==="
    0.48
    ru
    0.47
    irà
    0.46
    Eppo
    0.46
    宋
    0.46
    Cidade
    0.46
    POSITIVE LOGITS
     isopropyl
    0.55
     monomial
    0.49
     Deere
    0.48
     bisexual
    0.47
     lagging
    0.46
    сыпа
    0.46
     ubiquitin
    0.46
     flavonoid
    0.46
     Diels
    0.44
     psor
    0.43
    Activations Density 0.000%

    No Known Activations