© 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. 70504
    Prev
    Next
    INDEX
    Explanations

    high net worth

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

    listing items with punctuation

    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
    hala
    0.54
    delà
    0.51
    :'],
    0.48
    جیب
    0.47
    moto
    0.47
     öyle
    0.46
    ru
    0.46
    halle
    0.46
     عالی
    0.46
    subMenu
    0.46
    POSITIVE LOGITS
    oids
    0.54
     basking
    0.48
    狀
    0.48
     drinker
    0.47
    跳
    0.47
     finalizing
    0.46
     skipping
    0.46
     prioritization
    0.45
    無
    0.44
     labeling
    0.44
    Activations Density 0.000%

    No Known Activations