© 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. 24-GEMMASCOPE-2-RES-262K
    7. 5530
    Prev
    Next
    INDEX
    Explanations

    asking, achieving, looking, giving

    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_24_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
    這
    0.45
    Это
    0.44
     ज़िंदगी
    0.41
    但
    0.41
    Мы
    0.39
    Когда
    0.39
    Этот
    0.39
    Вот
    0.39
    this
    0.39
    ของเรา
    0.38
    POSITIVE LOGITS
    oretically
    0.62
    clusion
    0.55
    ählt
    0.51
    ductory
    0.50
    ación
    0.49
    đer
    0.48
    ological
    0.46
    1
    0.45
    ateboard
    0.45
    swering
    0.44
    Activations Density 0.180%

    No Known Activations