© 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. 53840
    Prev
    Next
    INDEX
    Explanations

    copyright notices

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

    copyright notices

    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
     drenched
    0.46
     நடித்த
    0.41
     \%)$,
    0.39
     drank
    0.38
    ‌
    0.38
    ེ
    0.38
     oblivious
    0.38
    ➞
    0.37
     Copyright
    0.37
    اعات
    0.37
    POSITIVE LOGITS
    owaniu
    0.43
     त्र
    0.41
    लब
    0.41
    क्
    0.41
     जेसीबी
    0.40
    helping
    0.40
    लट्
    0.40
    の効果
    0.39
    cludes
    0.37
    会自动
    0.37
    Activations Density 0.004%

    No Known Activations