© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 237724
    Prev
    Next
    INDEX
    Explanations

    or (alternatives)

    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
     घेतले
    0.52
    䞍
    0.51
     sillonné
    0.50
    nBitCount
    0.50
    बॉल
    0.49
     අ
    0.49
     dağı
    0.49
     १४
    0.49
    marginY
    0.49
    entingan
    0.49
    POSITIVE LOGITS
    u
    0.56
    e
    0.55
    i
    0.55
    \
    0.48
    s
    0.48
    weisung
    0.46
     used
    0.44
    as
    0.43
    sp
    0.43
     fuss
    0.42
    Activations Density 0.001%

    No Known Activations