© 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. 19174
    Prev
    Next
    INDEX
    Explanations

    this [item]

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

    multilingual context or explanation

    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
    َنْ
    0.42
     THIS
    0.41
    ست
    0.41
     SURVEY
    0.41
    FACTORY
    0.41
     this
    0.41
    関西
    0.41
     The
    0.40
    اسم
    0.40
    陽
    0.40
    POSITIVE LOGITS
     sempat
    0.53
     अतिरिक्त
    0.51
     그러나
    0.50
    ètres
    0.50
    िवारी
    0.48
     درخت
    0.48
    อื่นๆ
    0.47
     duet
    0.46
     ซึ่ง
    0.46
     घेतली
    0.46
    Activations Density 0.000%

    No Known Activations