© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 31155
    Prev
    Next
    INDEX
    Explanations

    steam

    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
     নিষ
    0.40
    mouseout
    0.40
    恣
    0.40
     paralysie
    0.40
     lâ
    0.38
    ്ര
    0.38
     discapacidad
    0.38
    袈
    0.38
     matriz
    0.38
     cropping
    0.38
    POSITIVE LOGITS
     steam
    3.39
     Steam
    3.25
    Steam
    3.23
    steam
    2.89
    蒸汽
    2.63
     steamed
    2.45
    STEAM
    2.27
     STEAM
    2.22
     steaming
    2.13
     steamers
    2.09
    Activations Density 0.006%

    No Known Activations