© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 144235
    Prev
    Next
    INDEX
    Explanations

    filed under, fruit jam

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

    starts of explanations or scenarios

    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
    Negative Logits
     hí
    0.52
     minions
    0.50
     madre
    0.50
     tám
    0.48
    ING
    0.48
     സമ്പ
    0.48
     koup
    0.47
     imprime
    0.47
     waar
    0.47
    ย
    0.47
    POSITIVE LOGITS
    тации
    0.56
    నుంది
    0.49
    者的
    0.47
     ইউনিয়নের
    0.46
    视角
    0.46
    జ్య
    0.44
    фесси
    0.44
    торы
    0.44
     вариант
    0.44
     తెలిప
    0.43
    Activations Density 0.001%

    No Known Activations