© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 284
    Prev
    Next
    INDEX
    Explanations

    API requests and methods

    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
     when
    -1.91
     about
    -1.65
     because
    -1.63
    !!!!
    -1.51
     więc
    -1.51
    山中
    -1.45
     preventing
    -1.41
     for
    -1.34
    ???
    -1.32
     When
    -1.30
    POSITIVE LOGITS
    without
    1.63
    since
    1.59
    through
    1.59
     illustre
    1.48
    both
    1.43
    within
    1.43
    today
    1.42
    each
    1.40
     várias
    1.40
     to
    1.39
    Activations Density 0.021%

    No Known Activations