© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 158664
    Prev
    Next
    INDEX
    Explanations

    homemade caramel

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

    familiar with Western and Eastern aesthetic theories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     visitors
    0.47
     rhizosphere
    0.47
    menes
    0.47
    р
    0.47
     captivated
    0.46
    quet
    0.46
     seroton
    0.46
     cataly
    0.45
    LEY
    0.45
     concomit
    0.45
    POSITIVE LOGITS
     Skipping
    0.53
     elég
    0.52
    衹
    0.51
     أكبر
    0.50
     Sélectionnez
    0.49
    បាន
    0.48
    姗
    0.47
     csak
    0.46
    essa
    0.46
     Faça
    0.45
    Activations Density 0.001%

    No Known Activations