© 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. 49150
    Prev
    Next
    INDEX
    Explanations

    it should

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

    ending terms like "Term" or numbers

    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
     lisse
    0.51
    VERTISE
    0.49
     dour
    0.49
    境界層
    0.47
    ↵↵↵
    0.47
     excitations
    0.46
     органів
    0.46
    チール
    0.46
    CLASSI
    0.46
     ferrovi
    0.46
    POSITIVE LOGITS
     goodbye
    0.80
    that
    0.70
     that
    0.62
     bahwa
    0.61
     it
    0.59
    gı
    0.58
     rằng
    0.57
    future
    0.57
    nothing
    0.57
    g
    0.55
    Activations Density 0.000%

    No Known Activations