© 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. 109951
    Prev
    Next
    INDEX
    Explanations

    Barbie, afternoon teas, primarily

    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
     அம்பேத்க
    0.52
     hại
    0.50
    的前提
    0.49
    فهام
    0.49
    istisch
    0.48
     atthakath
    0.48
    顓
    0.48
    ändige
    0.46
     Amend
    0.46
    equalTo
    0.45
    POSITIVE LOGITS
    *
    0.53
    h
    0.51
    "
    0.50
    im
    0.50
     and
    0.48
    つ
    0.48
    ियमित
    0.48
    r
    0.47
    t
    0.47
     for
    0.46
    Activations Density 0.003%

    No Known Activations