© 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. 206401
    Prev
    Next
    INDEX
    Explanations

    high degree

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

    contrasting elements

    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
    ুদ্ধে
    0.52
    ですから
    0.48
    事實
    0.48
    迲
    0.44
    TestCase
    0.44
    证据
    0.43
    ですので
    0.43
    ファ
    0.43
    下的
    0.42
    事実
    0.42
    POSITIVE LOGITS
     mab
    0.50
     qi
    0.46
     tib
    0.45
     teilen
    0.45
     yak
    0.44
    rante
    0.43
    حن
    0.42
     重
    0.42
     mā
    0.41
     resetting
    0.41
    Activations Density 0.000%

    No Known Activations