© 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. 165230
    Prev
    Next
    INDEX
    Explanations

    rooms include

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

    question words and topics

    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
    ኔታ
    0.49
    員
    0.48
    挖
    0.47
    队员
    0.46
    तेश
    0.45
    队长
    0.45
     সবাইকে
    0.45
    پرس
    0.44
    ён
    0.43
    児
    0.43
    POSITIVE LOGITS
     حركة
    0.42
     Θ
    0.41
    ichter
    0.40
     SMO
    0.39
     Фо
    0.39
     ヨ
    0.39
     Passo
    0.39
     وهذا
    0.39
     වන්නේ
    0.39
     murky
    0.38
    Activations Density 0.004%

    No Known Activations