© 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. 234731
    Prev
    Next
    INDEX
    Explanations

    general and in particular

    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
    One
    0.48
    или
    0.45
    вере
    0.44
    奋
    0.44
    ф
    0.42
    е
    0.42
    -
    0.42
    ซึ่ง
    0.41
    se
    0.41
     restante
    0.41
    POSITIVE LOGITS
     financials
    0.49
     myös
    0.47
     scholarships
    0.45
     পদ্ধ
    0.45
     malls
    0.45
     ɖ
    0.44
     các
    0.44
     সকল
    0.43
     phosphat
    0.42
     DISABLE
    0.42
    Activations Density 0.001%

    No Known Activations