© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 49667
    Prev
    Next
    INDEX
    Explanations

    business and industry terms

    np_acts-logits-general · gemini-2.5-flash-lite

    adding Ruy Lopez religious discrimination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     molecule
    0.45
     phosphorylation
    0.42
     অধিকাংশই
    0.42
     u
    0.42
     three
    0.42
     tsp
    0.41
     about
    0.41
     p
    0.41
     π
    0.40
     প্রথমেই
    0.40
    POSITIVE LOGITS
    ЕР
    0.60
    !”.
    0.59
    ៕
    0.58
    !"
    0.58
    !”
    0.57
    !".
    0.56
    "!
    0.55
    .
    0.55
    !।
    0.54
     🙏
    0.54
    Activations Density 0.093%

    No Known Activations