© 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. 4417
    Prev
    Next
    INDEX
    Explanations

    this paper investigates/examines/explores

    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
    ه
    0.86
    י
    0.65
    Según
    0.60
     zwią
    0.59
    Tesla
    0.58
    Aunque
    0.58
    Após
    0.58
    ق
    0.57
    بعد
    0.56
    ب
    0.56
    POSITIVE LOGITS
    asse
    0.73
    কারি
    0.63
    estic
    0.61
    ads
    0.61
    asters
    0.60
    становка
    0.59
    ський
    0.59
    ✶
    0.58
    ន៍
    0.57
    徑
    0.57
    Activations Density 0.005%

    No Known Activations