© 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. 100416
    Prev
    Next
    INDEX
    Explanations

    months of the year

    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
     in
    -2.36
     with
    -2.31
     for
    -2.20
     With
    -2.13
     from
    -2.05
     if
    -2.00
     There
    -1.99
     can
    -1.84
     through
    -1.82
     should
    -1.80
    POSITIVE LOGITS
    泚
    1.95
    一愣
    1.95
     própri
    1.81
    艄
    1.80
     linke
    1.80
    锨
    1.73
    茈
    1.73
    
    1.73
    畱
    1.72
    鶿
    1.70
    Activations Density 0.029%

    No Known Activations