© 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. 204534
    Prev
    Next
    INDEX
    Explanations

    commercial transactions and actions

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

    Mpemba effect, apple adds, framework

    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
     exotic
    0.51
     before
    0.50
     Lanes
    0.50
     før
    0.50
     Lanier
    0.49
     Ə
    0.48
     ennen
    0.47
     `'\\
    0.46
     Uh
    0.46
     McGowan
    0.46
    POSITIVE LOGITS
    Creo
    0.51
     интересных
    0.49
    Fecha
    0.48
    estruct
    0.47
    productos
    0.47
    ებისა
    0.44
    levant
    0.44
     графи
    0.44
     বিজনেস
    0.44
     Такой
    0.44
    Activations Density 0.003%

    No Known Activations