© 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. 7108
    Prev
    Next
    INDEX
    Explanations

    placeholder names

    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
     estekak
    -2.69
    ㌧
    -2.64
    只剩
    -2.48
     siguientes
    -2.47
     hinsichtlich
    -2.42
    笵
    -2.41
     bené
    -2.41
    怂
    -2.39
    мії
    -2.38
    垕
    -2.33
    POSITIVE LOGITS
     It
    3.13
    {
    2.88
    $
    2.75
     Its
    2.58
     sebaiknya
    2.55
    ли
    2.47
    </em>
    2.42
    ？！”
    2.39
     With
    2.38
     variés
    2.38
    Activations Density 0.001%

    No Known Activations