© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70571
    Prev
    Next
    INDEX
    Explanations

    that + verb clause

    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
    </h1>
    -1.70
    }$
    -1.68
     THE
    -1.59
    </strong>
    -1.55
     lament
    -1.54
    </h2>
    -1.53
    tedì
    -1.43
     і
    -1.41
     và
    -1.40
     и
    -1.39
    POSITIVE LOGITS
    In
    1.59
    ى
    1.52
     Água
    1.47
    €”
    1.43
    月に
    1.41
    $
    1.40
    驚く
    1.40
     Católica
    1.39
     Nieuws
    1.39
     warmen
    1.37
    Activations Density 0.123%

    No Known Activations