© 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-262K
    7. 44378
    Prev
    Next
    INDEX
    Explanations

    it's a

    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
     محکمہ
    0.48
    expressing
    0.44
     immerse
    0.42
    s
    0.42
    セ
    0.40
     Department
    0.40
     Ebay
    0.40
    。”
    0.39
     سل
    0.39
     immersing
    0.39
    POSITIVE LOGITS
    욥
    0.49
    ಟ್‌
    0.48
    ತ್ಮ
    0.47
    தல
    0.47
    imų
    0.46
    েরও
    0.45
    рақ
    0.45
    кин
    0.45
    ومان
    0.45
    ⵡ
    0.45
    Activations Density 0.003%

    No Known Activations