© 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. 209094
    Prev
    Next
    INDEX
    Explanations

    seen, assistants, remember, sticker

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

    checking, dates, contact

    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
    E
    0.47
    prime
    0.46
    H
    0.45
     unbek
    0.44
     dissol
    0.44
    وية
    0.44
    必要的
    0.44
     undec
    0.43
     اليس
    0.43
    匱
    0.43
    POSITIVE LOGITS
     फ्रेंड्स
    0.49
     मधु
    0.49
     सर्विसेज
    0.48
     ट्रेडिंग
    0.48
     यांचा
    0.45
     ОО
    0.45
     अवार्ड
    0.44
     कर्फ्यू
    0.44
     इं
    0.44
     जाग
    0.44
    Activations Density 0.000%

    No Known Activations