© 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. 34-GEMMASCOPE-RES-131K
    7. 57215
    Prev
    Next
    INDEX
    Explanations

    japanese animation and manga

    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_34/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
    <sub>
    -0.81
     pluma
    -0.79
     the
    -0.77
     Note
    -0.77
     algun
    -0.76
    呵呵
    -0.76
     our
    -0.75
     filmo
    -0.75
    のイメージ
    -0.74
     Emits
    -0.73
    POSITIVE LOGITS
    ーション
    0.97
     adaptation
    0.94
    inspired
    0.93
    Character
    0.88
     ferons
    0.87
    Inspired
    0.86
     décider
    0.86
     Shalom
    0.84
    XMLHttpRequest
    0.82
    phanumeric
    0.82
    Activations Density 0.016%

    No Known Activations