© 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. 124850
    Prev
    Next
    INDEX
    Explanations

    purchasing value and options

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

    protective sunglasses

    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
    کن
    0.49
     호출
    0.47
    静
    0.45
     Bộ
    0.44
    谚
    0.43
    铅
    0.43
     سریع
    0.42
     +:+
    0.42
    ोले
    0.42
    瑁
    0.42
    POSITIVE LOGITS
    ’
    0.52
    investment
    0.51
    ্যস্ত
    0.49
    field
    0.48
     massacre
    0.47
    purch
    0.47
    ir
    0.46
    purchase
    0.46
    pricing
    0.46
     retail
    0.46
    Activations Density 0.002%

    No Known Activations