© 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. 94899
    Prev
    Next
    INDEX
    Explanations

    practical/descriptive contexts

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

    python while loops

    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
    ر
    0.49
    里
    0.45
    ड्डा
    0.45
    MARK
    0.44
     contingency
    0.44
    ರ್ಗ
    0.43
    Ě
    0.43
    該
    0.43
    ير
    0.42
    frü
    0.42
    POSITIVE LOGITS
     yaşad
    0.51
     অর্থনীতির
    0.51
     ajoute
    0.49
     ষ
    0.49
     รวม
    0.48
     Osmanlı
    0.47
     অর্থনীতি
    0.47
     `:
    0.47
    acd
    0.47
    "',
    0.46
    Activations Density 0.000%

    No Known Activations