© 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-262K
    7. 203849
    Prev
    Next
    INDEX
    Explanations

    chills, mash, book, priest, 42

    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
    aitu
    0.43
    कालीन
    0.43
     عادة
    0.43
     Jer
    0.43
    <unused56>
    0.42
    ia
    0.41
    ेच्छा
    0.41
    ောင့်
    0.41
    attrs
    0.41
    ۰۰
    0.40
    POSITIVE LOGITS
    I
    0.49
     assumed
    0.46
     intensive
    0.46
     Amended
    0.46
     intracellular
    0.45
     amended
    0.45
     educated
    0.45
     novels
    0.45
     hybrid
    0.44
     impairs
    0.44
    Activations Density 0.001%

    No Known Activations