© 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. 246892
    Prev
    Next
    INDEX
    Explanations

    from, since, for, if

    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
    祁
    0.52
    Mountains
    0.49
    Erik
    0.47
    Cré
    0.45
    Paul
    0.44
     Zentral
    0.44
    znak
    0.44
     TERMS
    0.43
    蹺
    0.43
    قيقي
    0.42
    POSITIVE LOGITS
     emulsion
    0.51
     сен
    0.51
     сня
    0.50
     publicidad
    0.50
    ceiver
    0.50
     impresora
    0.47
     неожидан
    0.46
     emulsions
    0.46
    un
    0.46
     vehicular
    0.46
    Activations Density 0.000%

    No Known Activations