© 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. 224351
    Prev
    Next
    INDEX
    Explanations

    description: and this

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

    domain checker

    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
    ້ງ
    0.55
    Ნ
    0.51
    كبر
    0.50
    が通販
    0.50
    ÈRES
    0.50
     leichte
    0.49
    ودي
    0.49
    orderDetails
    0.49
     น้ํา
    0.48
     სიმ
    0.48
    POSITIVE LOGITS
     Page
    0.54
     Qu
    0.54
     Un
    0.51
     un
    0.49
     Robert
    0.48
     US
    0.48
    未
    0.46
     AI
    0.46
     Man
    0.45
     THE
    0.45
    Activations Density 0.001%

    No Known Activations