© 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. 210264
    Prev
    Next
    INDEX
    Explanations

    daily basis

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

    internal language generation

    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
    дар
    0.47
     proguard
    0.44
    aule
    0.43
    цію
    0.42
    noop
    0.42
     Zahl
    0.42
    一来
    0.42
     वर्षी
    0.40
    jsonObject
    0.40
    䐈
    0.40
    POSITIVE LOGITS
     मिन
    0.57
     можем
    0.50
     גם
    0.49
     पहाड़ी
    0.47
     junta
    0.47
     менее
    0.46
     innym
    0.46
    में
    0.46
     rappers
    0.46
     небольшой
    0.46
    Activations Density 0.000%

    No Known Activations