© 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. 60847
    Prev
    Next
    INDEX
    Explanations

    silicon chips

    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
     maar
    -1.78
    providedIn
    -1.64
    ële
    -1.57
     andere
    -1.56
     jeg
    -1.52
    createCanvas
    -1.41
    heten
    -1.34
     §
    -1.32
    beforeEach
    -1.32
     kun
    -1.31
    POSITIVE LOGITS
     sedia
    1.59
     dianggap
    1.53
    These
    1.52
     получается
    1.50
     pulsa
    1.48
    𝙟
    1.47
    楽しんで
    1.47
     tanpa
    1.45
     reseña
    1.42
     tasca
    1.41
    Activations Density 0.191%

    No Known Activations