© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 63297
    Prev
    Next
    INDEX
    Explanations

    gnosticism, awareness, exact dates, Pvt Ltd

    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_65k_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
     over
    0.59
     O
    0.53
    :
    0.51
     T
    0.50
     D
    0.49
     Heights
    0.49
     N
    0.48
     V
    0.48
     tailgate
    0.48
     solid
    0.46
    POSITIVE LOGITS
    我
    0.54
     ни
    0.49
    ⌞
    0.49
    blusas
    0.48
    ０
    0.48
     мм
    0.47
     симпто
    0.47
    Lub
    0.47
    эф
    0.46
    ал
    0.46
    Activations Density 0.005%

    No Known Activations