© 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. 25561
    Prev
    Next
    INDEX
    Explanations

    websites, links, and services

    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
     decreto
    -1.02
    Gilla
    -0.97
    IVIA
    -0.94
    Lindo
    -0.91
    Björn
    -0.90
     Posteriormente
    -0.89
    IRIT
    -0.88
    País
    -0.88
     огром
    -0.88
     plupart
    -0.88
    POSITIVE LOGITS
     about
    1.03
    の人は
    0.96
     wyłą
    0.90
    ầ
    0.89
    :
    0.88
    former
    0.86
     поможет
    0.85
    et
    0.84
    “
    0.84
     współ
    0.83
    Activations Density 0.007%

    No Known Activations