Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 24-GEMMASCOPE-2-RES-16K
    4. 11715
    Prev
    Next
    INDEX
    Explanations

    sentence continuations

    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_16k_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
    ุท
    0.62
    ὖ
    0.60
    irus
    0.59
     उन्‍ह
    0.58
    Dengan
    0.58
     quản
    0.57
    aság
    0.57
    upra
    0.57
     yüzde
    0.57
    Բ
    0.55
    POSITIVE LOGITS
     AKA
    0.64
     distinct
    0.59
     defining
    0.55
     context
    0.54
     technique
    0.54
     aka
    0.54
     grabbing
    0.54
     sondern
    0.54
     namun
    0.54
     teasing
    0.54
    Activations Density 0.227%

    No Known Activations