© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113288
    Prev
    Next
    INDEX
    Explanations

    words ending in berg, ith, cian, or Levi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </h3>
    -1.64
     freight
    -1.55
    Ⲉ
    -1.53
    “,
    -1.49
    */
    -1.47
    magem
    -1.45
     شوند
    -1.44
    تهى
    -1.44
     automotive
    -1.42
    ksiyon
    -1.42
    POSITIVE LOGITS
     is
    1.95
    Παραπομπές
    1.76
    特長
    1.51
     have
    1.44
    ویری
    1.41
     acompañado
    1.38
     was
    1.37
     his
    1.34
    rupulous
    1.33
    玊
    1.31
    Activations Density 0.035%

    No Known Activations