© 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. 84034
    Prev
    Next
    INDEX
    Explanations

    domain name

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

    and what

    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
     ፣
    0.55
     ฟัง
    0.54
    當
    0.53
    adığı
    0.52
    oubl
    0.51
    𝟎
    0.50
     `<=
    0.49
    的的
    0.49
    ۸
    0.48
     ถ้า
    0.47
    POSITIVE LOGITS
     Kit
    0.46
     pharmacology
    0.46
     bond
    0.44
     Linguistic
    0.44
     Bison
    0.43
     console
    0.43
     cafeteria
    0.43
     Bond
    0.42
     signage
    0.42
     Cher
    0.42
    Activations Density 0.000%

    No Known Activations