© 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. 34-GEMMASCOPE-RES-131K
    7. 63516
    Prev
    Next
    INDEX
    Explanations

    emerge or exit

    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_34/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
    Visiting
    -0.76
    operable
    -0.73
    ogueira
    -0.71
     Parry
    -0.71
    rierung
    -0.70
    become
    -0.69
     dimiliki
    -0.69
     יה
    -0.69
    ucci
    -0.69
    ível
    -0.68
    POSITIVE LOGITS
     emerge
    3.50
     emerges
    3.14
     exit
    3.13
     keluar
    3.13
     emerged
    3.11
     emerging
    2.86
     exiting
    2.84
    ออกมา
    2.70
     exited
    2.64
     exits
    2.63
    Activations Density 0.089%

    No Known Activations