© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 28809
    Prev
    Next
    INDEX
    Explanations

    evaluation or classification qualifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ನ್
    0.49
     своем
    0.46
     criticised
    0.41
     a
    0.39
     своём
    0.39
     आपले
    0.38
    ອກ
    0.37
    称
    0.37
    atsiya
    0.37
     Казіно
    0.36
    POSITIVE LOGITS
    س
    0.46
     توسط
    0.37
    وبات
    0.36
     oleh
    0.35
    ার্জি
    0.35
    ].
    0.34
    โดย
    0.34
    แก่
    0.34
    োর
    0.34
    ore
    0.33
    Activations Density 0.049%

    No Known Activations