© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 200252
    Prev
    Next
    INDEX
    Explanations

    develops, shoes, images, acting, use

    np_acts-logits-general · gemini-2.5-flash-lite

    end punctuation and formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itecture
    0.49
    这个问题
    0.45
    感受
    0.44
    adero
    0.43
    忘记
    0.42
    세를
    0.42
    したもの
    0.42
    <0xA9>
    0.41
    <0x88>
    0.40
     textArea
    0.40
    POSITIVE LOGITS
     Mannschaften
    0.55
     blames
    0.51
     tarz
    0.50
    𝚃
    0.50
     develops
    0.49
     Appeal
    0.49
     ら
    0.49
     disapproved
    0.49
     teams
    0.48
     saves
    0.48
    Activations Density 0.001%

    No Known Activations