© 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. 53-GEMMASCOPE-2-RES-65K
    7. 5583
    Prev
    Next
    INDEX
    Explanations

    BM followed by j or w

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

    BM25, BMAL1, BMX, BMTA

    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_53_width_65k_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
    slate
    0.42
    .*\
    0.41
    ípios
    0.38
    avo
    0.38
    Gad
    0.38
     criaturas
    0.37
    Quad
    0.36
    None
    0.36
     کب
    0.36
    *"
    0.36
    POSITIVE LOGITS
     Bold
    0.72
    Bold
    0.66
     bm
    0.66
     bold
    0.65
     BM
    0.55
    bold
    0.55
    bm
    0.54
    BOLD
    0.50
     bmp
    0.49
     BMD
    0.49
    Activations Density 0.001%

    No Known Activations