© 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. 7110
    Prev
    Next
    INDEX
    Explanations

    Ed followed by name or word

    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
    u
    -3.19
    e
    -3.00
    ᛬
    -2.53
    桖
    -2.50
    袛
    -2.50
    ornment
    -2.44
    ᠂
    -2.41
    </h4>
    -2.34
    鼱
    -2.34
    borderSide
    -2.31
    POSITIVE LOGITS
     This
    2.86
     Our
    2.70
     è
    2.56
    1
    2.41
     Welche
    2.41
    沺
    2.27
     ons
    2.23
     Why
    2.20
    これは
    2.19
     unprecedented
    2.14
    Activations Density 0.031%

    No Known Activations