© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81553
    Prev
    Next
    INDEX
    Explanations

    learn new things

    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_262k_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
     গ্রস্থ
    0.48
    zzel
    0.41
    oyne
    0.41
    젼
    0.40
     sheer
    0.39
    Ｈ
    0.39
    ET
    0.39
     foe
    0.39
     trif
    0.39
     margine
    0.39
    POSITIVE LOGITS
    Distinct
    0.47
    دا
    0.45
    运营
    0.45
    Page
    0.44
    啡
    0.44
    遒
    0.42
    姮
    0.42
     onboarding
    0.42
    distinct
    0.41
    สถานที่
    0.41
    Activations Density 0.005%

    No Known Activations