© 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. 10-GEMMASCOPE-RES-131K
    7. 7916
    Prev
    Next
    INDEX
    Explanations

    comedian

    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
    AdvEx
    -2.59
    nambuco
    -2.50
     stark
    -2.44
     that
    -2.42
    }+\
    -2.36
     Its
    -2.34
     horrifying
    -2.31
    蒾
    -2.23
     we
    -2.23
     vielen
    -2.22
    POSITIVE LOGITS
     That
    2.88
     They
    2.52
    er
    2.52
     tijden
    2.30
    
    2.28
    ꙮ
    2.28
     Они
    2.27
    焌
    2.25
     voeding
    2.22
     プレス
    2.22
    Activations Density 0.008%

    No Known Activations