© 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. 157267
    Prev
    Next
    INDEX
    Explanations

    usage of capacity

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

    product context, canvas painting, store front, school play

    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
    اگر
    0.52
    Organization
    0.51
     ingred
    0.48
     ہوگ
    0.48
    i
    0.46
    iation
    0.46
     Functions
    0.46
     Inhibition
    0.46
    栈
    0.46
    frastructure
    0.45
    POSITIVE LOGITS
    ਨ
    0.51
     مع
    0.50
    ਫ
    0.50
     ਅ
    0.50
    dividend
    0.48
    niki
    0.46
    RPG
    0.46
    mangle
    0.46
     පිළිබ
    0.46
     evrops
    0.45
    Activations Density 0.001%

    No Known Activations