© 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. 64786
    Prev
    Next
    INDEX
    Explanations

    UI element bindings

    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
     countless
    -1.42
     싶
    -1.41
     these
    -1.36
    opheles
    -1.34
     damen
    -1.33
     those
    -1.33
    Кроме
    -1.32
    𖡼
    -1.26
    鋮
    -1.26
    というわけで
    -1.24
    POSITIVE LOGITS
    </strong>
    1.62
     costos
    1.59
    </u>
    1.57
     áng
    1.55
    </b>
    1.54
     costes
    1.48
    </i>
    1.42
    ’
    1.41
    licherweise
    1.38
     negócios
    1.37
    Activations Density 0.001%

    No Known Activations