© 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. 80615
    Prev
    Next
    INDEX
    Explanations

    foreign and common english words

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

    resume summary

    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
    也很
    0.45
    提醒
    0.44
    小
    0.43
    但也
    0.42
    后再
    0.42
    他也
    0.41
    LOGO
    0.41
     Specialty
    0.40
    軺
    0.39
    RO
    0.39
    POSITIVE LOGITS
    tela
    0.50
     पाच
    0.50
     mempunyai
    0.49
     กราบ
    0.49
     palace
    0.48
     hendak
    0.48
     palpable
    0.48
     worrisome
    0.47
     murm
    0.47
     insinu
    0.46
    Activations Density 0.006%

    No Known Activations