© 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. 10-GEMMASCOPE-RES-131K
    7. 100723
    Prev
    Next
    INDEX
    Explanations

    delusions hallucinations orientation ramblings

    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
    </h1>
    -1.37
    </h5>
    -1.34
     ejemplar
    -1.29
    </i>
    -1.27
     trois
    -1.26
     לס
    -1.24
     мои
    -1.24
     you
    -1.23
    耷
    -1.23
     öfter
    -1.21
    POSITIVE LOGITS
    белый
    1.17
     Воло
    1.17
    ウェブサイト
    1.16
     incorporating
    1.15
    iglesia
    1.14
    大学の
    1.14
    産地
    1.13
    ꙳
    1.13
     بودند
    1.13
     Combining
    1.13
    Activations Density 0.038%

    No Known Activations