© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 60436
    Prev
    Next
    INDEX
    Explanations

    numbers and special characters

    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
     before
    -2.31
     when
    -2.13
     Before
    -2.00
     during
    -1.98
     after
    -1.94
     although
    -1.81
     but
    -1.81
     as
    -1.79
     Although
    -1.79
     Shortly
    -1.78
    POSITIVE LOGITS
     of
    2.20
     !!!!
    1.94
     quirky
    1.91
     !!!!!
    1.91
     unſ
    1.80
     seront
    1.80
    e
    1.80
     tranſ
    1.76
     myriad
    1.70
     overarching
    1.68
    Activations Density 0.002%

    No Known Activations