© 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. 113576
    Prev
    Next
    INDEX
    Explanations

    conference sporting events

    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
    </h3>
    -2.08
    が進
    -1.66
    {
    -1.56
    1
    -1.53
    But
    -1.52
     However
    -1.51
     entrées
    -1.46
     ドール
    -1.45
     oppure
    -1.44
    を進
    -1.44
    POSITIVE LOGITS
     &
    1.87
     theres
    1.66
     oscu
    1.60
     nasıl
    1.59
     cipolla
    1.52
    𝙰
    1.51
     如何
    1.50
     konus
    1.50
     teh
    1.49
     isnt
    1.49
    Activations Density 0.006%

    No Known Activations