© 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. 148
    Prev
    Next
    INDEX
    Explanations

    special characters or formatting

    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
     If
    -1.71
     Before
    -1.65
    靄
    -1.59
     This
    -1.56
     six
    -1.45
     When
    -1.44
    r
    -1.44
     get
    -1.44
     before
    -1.42
     four
    -1.42
    POSITIVE LOGITS
     latest
    1.82
     also
    1.72
     maniere
    1.67
     predominantly
    1.57
     soooo
    1.55
     largely
    1.55
     pittores
    1.55
     verbe
    1.53
     sooo
    1.53
     agres
    1.53
    Activations Density 0.009%

    No Known Activations