© 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. 203689
    Prev
    Next
    INDEX
    Explanations

    materials, food, and media series

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

    WHR, CMMC, comparable

    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
    社会主义
    0.52
     financi
    0.45
     UINavigation
    0.44
     ज़रूरत
    0.44
     받을
    0.44
    🫰
    0.44
     좌
    0.44
     날
    0.44
     사회
    0.44
     MOQ
    0.43
    POSITIVE LOGITS
    CCc
    0.50
    MRC
    0.49
    AP
    0.48
    CC
    0.48
     garnered
    0.48
     concentrates
    0.47
    AF
    0.46
    gF
    0.46
    percent
    0.46
    gp
    0.46
    Activations Density 0.001%

    No Known Activations