© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64603
    Prev
    Next
    INDEX
    Explanations

    IFLY crew, Iker Formula, Iwakuni, Iñigo Quilez, Ilex, Ioflupane

    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
    Massive
    -0.82
     Massive
    -0.79
    кот
    -0.78
    זה
    -0.77
     NP
    -0.77
    麟
    -0.77
     frumos
    -0.76
     frische
    -0.76
    χ
    -0.76
     груп
    -0.75
    POSITIVE LOGITS
     može
    0.82
     sincer
    0.79
     chastity
    0.78
     مواقع
    0.77
    owanie
    0.75
    erialization
    0.75
    血糖
    0.74
     sufic
    0.74
     correg
    0.73
    hasMore
    0.72
    Activations Density 0.696%

    No Known Activations