© 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. 64552
    Prev
    Next
    INDEX
    Explanations

    replacement reminder

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

    Option 1

    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
    ορ
    0.58
    。
    0.52
    עם
    0.49
    フラ
    0.43
    んです
    0.43
     intimidating
    0.42
     frightening
    0.42
    ır
    0.41
    வில
    0.41
    бар
    0.41
    POSITIVE LOGITS
    netje
    0.53
     കാരണ
    0.52
    benhav
    0.49
     नीतियों
    0.49
     ////
    0.48
     〢
    0.46
     नी
    0.45
     నీ
    0.45
     
    0.45
     الفق
    0.45
    Activations Density 0.000%

    No Known Activations