© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 10142
    Prev
    Next
    INDEX
    Explanations

    flooring, ceilings, countertops

    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
     that
    -2.16
     it
    -1.81
     from
    -1.69
    t
    -1.67
     for
    -1.67
     Of
    -1.63
    </tr>
    -1.59
     because
    -1.59
     or
    -1.58
    A
    -1.58
    POSITIVE LOGITS
     brasileira
    1.58
     persiste
    1.56
     ultime
    1.48
    後記
    1.48
     spesial
    1.42
     pittores
    1.39
     légumes
    1.38
     Quelle
    1.38
     rurale
    1.37
     stille
    1.36
    Activations Density 0.019%

    No Known Activations