© 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. 182495
    Prev
    Next
    INDEX
    Explanations

    statement of purpose

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

    If I provide

    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
    邉
    0.45
    ző
    0.44
     edging
    0.44
     ঘটনার
    0.44
     أيضًا
    0.43
    kinen
    0.43
    <unused32>
    0.42
     meestal
    0.42
     geweld
    0.41
     உ
    0.41
    POSITIVE LOGITS
    पीडी
    0.54
    тип
    0.50
     dạy
    0.49
    кон
    0.49
    лега
    0.48
     रजिस्टर
    0.48
     सहकारी
    0.47
    ர்ஸ்
    0.47
    тели
    0.47
    어졌
    0.47
    Activations Density 0.000%

    No Known Activations