© 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. 233842
    Prev
    Next
    INDEX
    Explanations

    setup, Exceeds, Single Exposure

    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
     と
    0.50
     ő
    0.48
     হেফাজতে
    0.46
     س
    0.46
     ajout
    0.46
     öt
    0.46
     गिरफ्तार
    0.46
     إ
    0.44
    த
    0.44
     ط
    0.43
    POSITIVE LOGITS
    वण्यासाठी
    0.48
    ঈদ
    0.47
    ἆ
    0.46
    programmer
    0.46
    슝
    0.45
     پروگرام
    0.44
    ivität
    0.44
    ჭირ
    0.44
    鱻
    0.44
    icultura
    0.44
    Activations Density 0.001%

    No Known Activations