© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62937
    Prev
    Next
    INDEX
    Explanations

    initial public offering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    memberOf
    -0.76
     لئے
    -0.76
     dataSnapshot
    -0.75
    promo
    -0.75
     رسیده
    -0.75
    lades
    -0.72
     transmisión
    -0.71
    prize
    -0.69
    不動産
    -0.69
    学校
    -0.69
    POSITIVE LOGITS
     IPO
    4.38
    IPO
    3.05
    ipo
    2.28
     ipo
    2.23
     Initial
    2.08
     initial
    1.84
    Initial
    1.70
     listing
    1.65
    上市
    1.59
     flotation
    1.50
    Activations Density 0.025%

    No Known Activations