© 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. 59145
    Prev
    Next
    INDEX
    Explanations

    door

    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
    THERE
    -1.88
    those
    -1.59
    悧
    -1.56
    They
    -1.52
    Designed
    -1.51
    having
    -1.50
     dì
    -1.49
    äuser
    -1.48
    WHY
    -1.45
    ఝ
    -1.45
    POSITIVE LOGITS
     what
    1.64
     after
    1.62
     two
    1.58
     sowohl
    1.57
     podczas
    1.52
    によって
    1.50
     knows
    1.48
     history
    1.46
     determines
    1.45
     embodies
    1.43
    Activations Density 0.010%

    No Known Activations