© 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. 172012
    Prev
    Next
    INDEX
    Explanations

    religious denominations and days

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

    descriptive phrases and code definitions

    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
    槊
    0.43
     technischen
    0.43
     obj
    0.40
     fluxes
    0.40
    visi
    0.40
    zellen
    0.40
     utilisez
    0.39
    zones
    0.39
     Shadow
    0.39
    usercontent
    0.39
    POSITIVE LOGITS
    сси
    0.49
     retirement
    0.42
    நீ
    0.42
    вање
    0.42
    ван
    0.41
    п
    0.41
    ৰ
    0.41
    탓
    0.41
     налого
    0.41
     concerto
    0.40
    Activations Density 0.003%

    No Known Activations