© 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. 31-GEMMASCOPE-2-RES-262K
    7. 204125
    Prev
    Next
    INDEX
    Explanations

    rolling stock, liquid outlets, situation

    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_31_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
    0
    0.54
     soiled
    0.48
    _
    0.46
    2
    0.46
     as
    0.45
     Full
    0.45
    1
    0.43
    ная
    0.43
     Tìm
    0.41
     Lak
    0.41
    POSITIVE LOGITS
    पतवार
    0.51
     प्राइस
    0.50
    НР
    0.50
    𝗘
    0.49
     assuntos
    0.49
    𝗪
    0.48
    𝗙
    0.48
    𝗠
    0.47
     वाजिब
    0.46
     പദ്ധതി
    0.46
    Activations Density 0.001%

    No Known Activations