© 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. 22-GEMMASCOPE-RES-131K
    7. 129024
    Prev
    Next
    INDEX
    Explanations

    "Eureka!" or questions

    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_22/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
    Banyak
    -1.23
    깐
    -1.13
    ＞＞
    -1.12
    さてさて
    -1.09
    Semua
    -1.07
    Много
    -1.05
    Hanya
    -1.05
    を
    -1.04
    とにかく
    -1.02
    さすが
    -1.02
    POSITIVE LOGITS
    pointers
    0.99
    changer
    0.95
    Geological
    0.94
    琀
    0.91
     atlantic
    0.91
     fortsätter
    0.89
    Uro
    0.88
    /**
    0.86
     —
    0.85
    ARCHITECT
    0.85
    Activations Density 0.000%

    No Known Activations