© 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-65K
    7. 8574
    Prev
    Next
    INDEX
    Explanations

    practical information about

    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
    gä
    0.44
     सारे
    0.40
    帶來
    0.40
    ਸ਼
    0.40
    嗄
    0.39
    特殊
    0.39
    っぷ
    0.38
    𝘨
    0.38
    錢
    0.38
    สด
    0.38
    POSITIVE LOGITS
     How
    0.49
    cych
    0.47
    How
    0.43
     útil
    0.42
     Neo
    0.42
    Coat
    0.42
    Useful
    0.41
     Dog
    0.41
     Useful
    0.40
     Helpful
    0.40
    Activations Density 0.003%

    No Known Activations