© 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. 209518
    Prev
    Next
    INDEX
    Explanations

    persistent diarrhea

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

    mathematics and authentication

    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
    ه
    0.53
    ام
    0.52
    THUR
    0.51
    不同的
    0.50
    اد
    0.49
    мой
    0.46
    homeini
    0.45
    阊
    0.45
     श्रीनगर
    0.44
    इस्
    0.44
    POSITIVE LOGITS
     Polynomial
    0.49
     সারাদেশে
    0.46
     세제곱
    0.46
     cowling
    0.44
     розвитку
    0.44
     more
    0.43
     klasy
    0.43
     sequential
    0.43
     gravit
    0.43
     যন্ত্র
    0.42
    Activations Density 0.001%

    No Known Activations