© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 38250
    Prev
    Next
    INDEX
    Explanations

    the reports

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

    things that change

    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
     із
    0.42
     ex
    0.41
     đột
    0.41
     in
    0.40
    祚
    0.40
     effectual
    0.40
     تعليم
    0.40
     apreciar
    0.39
     تحليل
    0.39
     مشابه
    0.39
    POSITIVE LOGITS
    филлер
    0.50
     chargingStation
    0.50
    পাঁ
    0.47
    hepat
    0.46
     fours
    0.46
    छे
    0.45
     帽
    0.45
     هستیم
    0.45
     fyra
    0.45
     नारी
    0.44
    Activations Density 0.000%

    No Known Activations