© 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. 25561
    Prev
    Next
    INDEX
    Explanations

    Nobel Prize, huge flocks

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

    keywords followed by specific punctuation

    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
     uczniów
    0.49
     öğret
    0.46
     विद्यार्थ्यांनी
    0.43
     শিক্ষার্থী
    0.41
    translator
    0.40
    ီး
    0.39
     Florida
    0.39
    黉
    0.39
     الطلاب
    0.39
    纲
    0.38
    POSITIVE LOGITS
    urra
    0.49
     honesty
    0.47
     verificar
    0.47
    хбет
    0.46
     stupidity
    0.45
     stalking
    0.45
    لاسه
    0.44
     Rahim
    0.44
     проверки
    0.44
     ceasefire
    0.44
    Activations Density 0.000%

    No Known Activations