© 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-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 113396
    Prev
    Next
    INDEX
    Explanations

    sea in

    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
     by
    -1.84
    TestingModule
    -1.77
    and
    -1.68
     =
    -1.61
    al
    -1.60
     these
    -1.59
     those
    -1.59
    ())),
    -1.54
    ol
    -1.52
     '/':
    -1.48
    POSITIVE LOGITS
     meravigli
    1.73
     unending
    1.72
     cancelamento
    1.64
     soooo
    1.64
     sooo
    1.64
     firmy
    1.64
    栳
    1.63
    
    1.55
     cavalo
    1.55
    selbe
    1.54
    Activations Density 0.087%

    No Known Activations