© 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. 40-GEMMASCOPE-2-RES-262K
    7. 214746
    Prev
    Next
    INDEX
    Explanations

    format presentation instructions

    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_40_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
    這麼
    0.43
     veg
    0.42
    抿
    0.41
    withProperties
    0.41
    regener
    0.40
     مني
    0.40
    attacking
    0.39
    vercel
    0.39
    nb
    0.37
     exponents
    0.37
    POSITIVE LOGITS
     Install
    0.38
     सिया
    0.38
     Installation
    0.37
    安装
    0.36
     ලි
    0.36
    >¯</
    0.36
    iidae
    0.35
     Archaeology
    0.35
     Installing
    0.35
     installed
    0.35
    Activations Density 0.000%

    No Known Activations