© 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. 21882
    Prev
    Next
    INDEX
    Explanations

    women and children's

    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
     margins
    -1.43
     gän
    -1.41
     that
    -1.39
    𓍊
    -1.38
    }$
    -1.38
    3
    -1.36
     höchsten
    -1.34
    ):
    -1.34
     jahr
    -1.34
    mell
    -1.32
    POSITIVE LOGITS
    /*@
    1.44
    orical
    1.38
    れたら
    1.35
    al
    1.34
     &#
    1.29
     saine
    1.28
    circled
    1.24
    
    1.22
    cessed
    1.20
    CREDIT
    1.20
    Activations Density 0.051%

    No Known Activations