© 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-65K
    7. 45608
    Prev
    Next
    INDEX
    Explanations

    maximum limits or quantities

    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
    ون
    0.71
     axons
    0.67
     aromas
    0.65
     acides
    0.65
     mosaics
    0.64
    Та
    0.63
    preferences
    0.62
    A
    0.61
     baryons
    0.61
    Embarked
    0.60
    POSITIVE LOGITS
     for
    0.70
    ס
    0.63
    ody
    0.59
    for
    0.58
     max
    0.57
    不超过
    0.57
    max
    0.57
     максима
    0.57
     maximum
    0.56
    สูงสุด
    0.56
    Activations Density 0.045%

    No Known Activations