© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 33214
    Prev
    Next
    INDEX
    Explanations

    Pullman railroad Sleeping Cars

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rov
    0.41
    template
    0.36
    emotion
    0.36
     friendship
    0.36
     outre
    0.36
    Template
    0.35
     tempt
    0.35
    🔟
    0.35
    out
    0.35
    ppets
    0.35
    POSITIVE LOGITS
     Vanderbilt
    0.59
     Leland
    0.56
     Pullman
    0.55
     Cornelius
    0.52
     COR
    0.52
     railroad
    0.52
     Railroad
    0.51
    Sleeping
    0.51
     Sleeping
    0.49
     railroads
    0.48
    Activations Density 0.002%

    No Known Activations