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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 6136
    Prev
    Next
    INDEX
    Explanations

    provide information

    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
    시켜
    1.47
     convening
    1.47
    ()=>{
    1.46
     bogged
    1.42
    ties
    1.41
    是多少
    1.41
    觑
    1.41
    )
    1.40
     fibroblasts
    1.38
     fists
    1.38
    POSITIVE LOGITS
    kannya
    1.88
    itre
    1.80
    า
    1.74
    та
    1.66
    quele
    1.64
    على
    1.63
     Pestic
    1.62
    в
    1.59
    ឲ
    1.59
    ли
    1.57
    Activations Density 0.188%

    No Known Activations