© 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. 59264
    Prev
    Next
    INDEX
    Explanations

    part 1

    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
    {
    -2.20
    Usually
    -1.96
     NOTE
    -1.93
     There
    -1.92
    astricht
    -1.77
    </b>
    -1.70
    Since
    -1.65
    there
    -1.64
    Because
    -1.64
     During
    -1.63
    POSITIVE LOGITS
     ktore
    2.02
    ༀ
    1.99
    ☫
    1.88
     bytu
    1.86
     incluso
    1.70
     brinde
    1.66
    轳
    1.65
     estable
    1.64
     București
    1.62
    掂
    1.60
    Activations Density 0.058%

    No Known Activations