© 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. 101230
    Prev
    Next
    INDEX
    Explanations

    living together

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

    explaining resumes

    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
    ्यानंतर
    0.47
     الإمارات
    0.44
     Binance
    0.44
     للغاية
    0.44
    Utc
    0.42
    ে
    0.41
     সময়ে
    0.40
     الماض
    0.39
     الصوت
    0.39
    瞎
    0.39
    POSITIVE LOGITS
     dios
    0.52
     Questi
    0.50
     couvre
    0.49
     presenting
    0.48
     gravit
    0.48
     Questo
    0.48
     pectin
    0.48
     který
    0.47
     cuya
    0.46
     whose
    0.46
    Activations Density 0.002%

    No Known Activations