© 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. 38143
    Prev
    Next
    INDEX
    Explanations

    Kelly's Directory or are just

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

    AI advancement and availability

    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
    及
    0.49
    快
    0.46
    曾
    0.46
    <0xE3>
    0.45
    nent
    0.43
    ná
    0.42
    }`);
    0.41
    去年
    0.41
    防
    0.41
    нут
    0.40
    POSITIVE LOGITS
    綵
    0.51
     সতর্কতা
    0.49
    ۰
    0.48
    []>
    0.48
    sever
    0.47
     Crater
    0.47
    getProperty
    0.46
    명의
    0.46
    aughey
    0.46
    oje
    0.46
    Activations Density 0.000%

    No Known Activations