© 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. 1594
    Prev
    Next
    INDEX
    Explanations

    domestic customers, branches of, get married

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

    transition to, led to, improve operational

    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
     বৎসর
    0.31
     পৃষ্ঠা
    0.31
     giáo
    0.31
    mUserManager
    0.29
     апреле
    0.29
     উপস্থিত
    0.29
     গ্রন্থে
    0.29
     ?>">
    0.29
     লিখিতে
    0.29
    >$
    0.28
    POSITIVE LOGITS
     tüm
    0.51
     dodat
    0.43
     nawet
    0.42
     kom
    0.42
     konfigur
    0.42
     risiko
    0.42
     incluso
    0.40
     deaktiv
    0.40
     grumpy
    0.39
     Optionen
    0.39
    Activations Density 0.051%

    No Known Activations