© 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. 39344
    Prev
    Next
    INDEX
    Explanations

    verbs preceding punctuation/nouns

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

    encoder-decoder architectures

    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
     Chia
    0.43
    os
    0.42
     açıklam
    0.42
     riqueza
    0.41
    巧妙
    0.41
    ﺿ
    0.41
    function
    0.40
     capacità
    0.39
    APPLICATION
    0.39
    曲
    0.39
    POSITIVE LOGITS
     勝
    0.52
    izdat
    0.52
     เด่น
    0.51
     منتقل
    0.49
    ❕
    0.48
    იან
    0.48
    ründ
    0.47
    ądź
    0.47
    ectady
    0.46
    𝙢
    0.46
    Activations Density 0.000%

    No Known Activations