© 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. 113406
    Prev
    Next
    INDEX
    Explanations

    tapping interfaces or on-screen elements

    np_acts-logits-general · gemini-2.5-flash-lite

    the word "tap" in the context of touchscreen or user interface interactions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    </h3>
    -2.09
     начали
    -1.66
     Sicherung
    -1.62
     Aussagen
    -1.55
    !”
    -1.55
    }-
    -1.53
     チキン
    -1.51
    },
    -1.46
    /";
    -1.46
    也
    -1.45
    POSITIVE LOGITS
    这件事
    1.48
    
    1.45
    𝙜
    1.45
    这事
    1.41
     about
    1.40
    繖
    1.39
    "
    1.38
    这件事情
    1.38
    ܃
    1.30
    𐐀
    1.30
    Activations Density 0.013%

    No Known Activations