© 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. 204898
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation or verbs

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

    processing pairs of items

    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
     _
    0.44
     बाकी
    0.43
     空
    0.43
     non
    0.42
    ê
    0.42
     े
    0.42
     言
    0.41
    +}\
    0.41
     何
    0.41
    idic
    0.41
    POSITIVE LOGITS
    муще
    0.43
    মাত্র
    0.42
     empresario
    0.40
    itelji
    0.40
    觎
    0.39
     institución
    0.38
     mayors
    0.38
    趔
    0.38
    相手
    0.37
    另一个
    0.37
    Activations Density 0.004%

    No Known Activations