© 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. 29407
    Prev
    Next
    INDEX
    Explanations

    roles before prepositions or conjunctions

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

    specific compound nouns

    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
    ！！！
    0.42
     qualifies
    0.40
    頔
    0.38
     impresionante
    0.37
    ！！！！
    0.36
     opted
    0.35
     trademark
    0.35
     hairline
    0.35
     dần
    0.35
     inked
    0.34
    POSITIVE LOGITS
    ᖕ
    0.42
    ட்டில்
    0.36
    घटना
    0.36
    motionProxy
    0.35
    학생
    0.34
     열심히
    0.34
    КИ
    0.34
     война
    0.34
    그래서
    0.33
    संध
    0.33
    Activations Density 0.008%

    No Known Activations