© 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. 225019
    Prev
    Next
    INDEX
    Explanations

    burn with, are great, Syrian regime

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

    phrase name property or technical terms

    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
     Scrub
    0.52
    i
    0.48
    u
    0.48
    n
    0.47
     androidx
    0.47
    k
    0.46
    bear
    0.45
     赵
    0.45
     Force
    0.44
     Meng
    0.44
    POSITIVE LOGITS
    Lorsque
    0.54
    UY
    0.52
    ਿਲ
    0.50
    helping
    0.48
    RA
    0.48
    ৫
    0.46
     lParam
    0.44
    ется
    0.44
    heta
    0.44
    UW
    0.44
    Activations Density 0.000%

    No Known Activations