© 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. 175542
    Prev
    Next
    INDEX
    Explanations

    Camilla, color, attacks, stimulated

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

    legal, clinical, autoencoder, transformations, original sin

    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
    زيد
    0.53
     internasional
    0.53
    export
    0.52
     statunitense
    0.52
    Č
    0.51
     internazionali
    0.50
    CE
    0.50
     internationale
    0.50
     américain
    0.50
     internazionale
    0.49
    POSITIVE LOGITS
    .‏
    0.56
     ата
    0.53
     भग
    0.51
    stimulated
    0.51
    attacks
    0.47
    իմ
    0.47
     셀
    0.47
     آیات
    0.46
    shareButton
    0.46
     لاب
    0.45
    Activations Density 0.000%

    No Known Activations