© 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. 66838
    Prev
    Next
    INDEX
    Explanations

    great followed by a descriptor

    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
    instead
    -1.38
    ometers
    -1.34
    瓒
    -1.27
    telse
    -1.21
     eigentlich
    -1.20
     zuständig
    -1.20
    “
    -1.16
     ursprünglich
    -1.16
     Ν
    -1.16
     Instead
    -1.16
    POSITIVE LOGITS
     also
    1.18
    SDA
    1.16
    ",
    1.15
     przysz
    1.15
     myös
    1.14
    </i>
    1.13
     względem
    1.13
    ercizi
    1.11
    ьому
    1.11
     miesz
    1.09
    Activations Density 0.052%

    No Known Activations