Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 25967
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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)
    273,612 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    瑚
    0.40
     MIR
    0.39
    ముఖ
    0.39
     dirigir
    0.38
     CURL
    0.38
     glTex
    0.38
     вър
    0.38
     IU
    0.38
     MTLTexture
    0.38
    漁
    0.38
    POSITIVE LOGITS
    use
    0.48
    Scopes
    0.44
    scopes
    0.43
    azi
    0.42
    property
    0.41
    詑
    0.39
    scope
    0.39
    resx
    0.39
    ami
    0.38
    ili
    0.37
    Activations Density 0.003%

    No Known Activations