© 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. 22-GEMMASCOPE-RES-131K
    7. 14155
    Prev
    Next
    INDEX
    Explanations

    special characters, code, and math

    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
     razones
    -1.10
     satisfa
    -1.09
     desper
    -1.09
     opiniones
    -1.07
    ksesta
    -1.05
    ࿚
    -1.04
     mutter
    -1.03
    の水
    -1.03
     comenz
    -1.02
     ohne
    -1.02
    POSITIVE LOGITS
     that
    1.90
     it
    1.41
     they
    1.27
    它
    1.18
     次元
    1.15
    これは
    1.14
    当然
    1.13
    紘
    1.12
     by
    1.12
     how
    1.11
    Activations Density 0.139%

    No Known Activations