© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 32101
    Prev
    Next
    INDEX
    Explanations

    basic needs and fulfillment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    复制代码
    1.16
     segno
    1.05
     ago
    1.04
    <0x80>
    1.03
     lũ
    0.98
     majeur
    0.97
    ത്യ
    0.96
    </h3>
    0.95
     côt
    0.95
     Ә
    0.94
    POSITIVE LOGITS
    ع
    1.48
    t
    1.39
    ez
    1.38
    ا
    1.35
    ла
    1.27
    as
    1.26
    hellip
    1.26
    aus
    1.22
    aust
    1.20
    ی
    1.18
    Activations Density 0.013%

    No Known Activations