© 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. 20252
    Prev
    Next
    INDEX
    Explanations

    comparison and replacement

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

    contrast conjunctions

    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
    なかった
    0.41
    дент
    0.40
    preprocess
    0.40
    тус
    0.40
    usus
    0.39
    したら
    0.38
    二
    0.38
    をした
    0.38
    क्योंकि
    0.38
    岳
    0.38
    POSITIVE LOGITS
     সবই
    0.46
     semua
    0.45
     তবু
    0.45
     stets
    0.44
     अधिकांश
    0.43
     wszel
    0.43
     অধিকাংশ
    0.43
     যতই
    0.42
     paura
    0.42
     każdego
    0.42
    Activations Density 0.012%

    No Known Activations