© 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. 145381
    Prev
    Next
    INDEX
    Explanations

    home, laundry, and items

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

    monitors

    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
    oja
    0.53
    l
    0.51
    Scotland
    0.49
    NR
    0.47
    Office
    0.47
     સર
    0.47
    lent
    0.46
    rzed
    0.46
     ઓફ
    0.46
    owanie
    0.46
    POSITIVE LOGITS
    َت
    0.45
    分為
    0.43
     weight
    0.43
     twos
    0.43
     clothes
    0.43
     multiples
    0.42
     pilgrimage
    0.42
     dev
    0.42
    케
    0.41
     infusion
    0.41
    Activations Density 0.001%

    No Known Activations