© 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. 99121
    Prev
    Next
    INDEX
    Explanations

    needed to / required for

    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
    usions
    -1.71
    they
    -1.62
     cordones
    -1.61
     condicionado
    -1.53
     brancas
    -1.50
     vermelhas
    -1.49
     suela
    -1.48
     ワゴン
    -1.47
    　　　　　　　
    -1.45
    !»
    -1.43
    POSITIVE LOGITS
     to
    2.81
     for
    2.14
     of
    1.68
     between
    1.53
     You
    1.47
     until
    1.47
     Another
    1.45
    臾
    1.40
     from
    1.35
     oppure
    1.34
    Activations Density 0.034%

    No Known Activations