© 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. 152258
    Prev
    Next
    INDEX
    Explanations

    addition, upon, over

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

    language and code

    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
    0
    0.62
    s
    0.48
    si
    0.46
     Parts
    0.45
     Bund
    0.42
    2
    0.40
     intestine
    0.40
     singleton
    0.39
    礼
    0.39
    hou
    0.39
    POSITIVE LOGITS
     deviations
    0.54
     unbeliev
    0.51
    である
    0.50
     ดังนั้น
    0.50
    έ
    0.50
     TESTS
    0.49
     হওয়ায়
    0.49
     dirigido
    0.49
    अब
    0.48
    だと
    0.48
    Activations Density 0.000%

    No Known Activations