© 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. 136129
    Prev
    Next
    INDEX
    Explanations

    a bit

    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
     mancan
    0.62
     concom
    0.50
    トマト
    0.49
     dô
    0.49
     surgir
    0.48
     ομά
    0.47
    
    0.46
    ⬝
    0.46
     كوساين
    0.46
     yatha
    0.46
    POSITIVE LOGITS
    s
    0.51
     Panel
    0.49
    an
    0.48
     on
    0.46
     U
    0.46
    0.46
    ando
    0.45
    ime
    0.44
    ice
    0.43
    Panel
    0.43
    Activations Density 0.007%

    No Known Activations