© 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. 112922
    Prev
    Next
    INDEX
    Explanations

    is defined

    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
     and
    -1.64
    cvtColor
    -1.37
    utveck
    -1.23
     ejercicios
    -1.20
     BorderRadius
    -1.19
    ıt
    -1.19
    ಠ
    -1.19
     FontWeight
    -1.18
    ċi
    -1.18
     anci
    -1.17
    POSITIVE LOGITS
     you
    1.77
     other
    1.66
    これからも
    1.32
     others
    1.31
     most
    1.29
     use
    1.27
    Other
    1.27
     there
    1.23
     інших
    1.23
     this
    1.21
    Activations Density 0.309%

    No Known Activations