© 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. 55059
    Prev
    Next
    INDEX
    Explanations

    unique words and subsequent actions

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

    describing common phrases and concepts

    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
    յ
    0.48
    다
    0.46
    시다
    0.46
    را
    0.45
     بتا
    0.44
    خل
    0.44
    Всем
    0.44
    ਨ
    0.44
    น้ำ
    0.43
    Así
    0.43
    POSITIVE LOGITS
     packageName
    0.46
    牛乳
    0.46
    ordat
    0.46
     গাঙ্গুল
    0.46
    ck
    0.45
    ുള്ള
    0.44
    噎
    0.44
     নিয়ত
    0.43
    ঞ্ছ
    0.43
    HTMLElement
    0.42
    Activations Density 0.000%

    No Known Activations