© 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. 70215
    Prev
    Next
    INDEX
    Explanations

    code comments and documentation

    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
     コート
    -1.82
     vorhand
    -1.70
     '-')
    -1.67
     خمس
    -1.65
     PROCEEDINGS
    -1.63
    鐿
    -1.63
     bahkan
    -1.63
     câbles
    -1.61
    same
    -1.59
    BatchNorm
    -1.58
    POSITIVE LOGITS
     or
    2.16
    </h2>
    2.02
     may
    1.97
     such
    1.84
    </h1>
    1.83
     has
    1.77
     always
    1.77
     can
    1.74
     in
    1.72
     appears
    1.72
    Activations Density 0.008%

    No Known Activations