© 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. 16-GEMMASCOPE-2-RES-262K
    7. 34887
    Prev
    Next
    INDEX
    Explanations

    steam or vapor

    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/layer_16_width_262k_l0_medium
    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
     hemolytic
    0.59
    ิ
    0.57
    ime
    0.56
     साथी
    0.55
    ۔
    0.54
    oblastic
    0.54
    ampton
    0.53
    astica
    0.53
    お金
    0.52
    political
    0.52
    POSITIVE LOGITS
     steam
    1.05
     Steam
    1.00
    Steam
    0.93
    蒸汽
    0.91
    蒸
    0.89
     vapeur
    0.87
     vapor
    0.86
     steamed
    0.85
    氤
    0.84
     Vapor
    0.84
    Activations Density 0.025%

    No Known Activations