© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 44801
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     siku
    0.84
    ()=>{
    0.84
     puedan
    0.82
     anni
    0.81
     jamás
    0.80
     vier
    0.79
     plano
    0.79
     pudieran
    0.79
     grupo
    0.78
     mantenerse
    0.78
    POSITIVE LOGITS
    y
    0.82
    istique
    0.81
     त्यात
    0.80
    ous
    0.80
    дных
    0.79
    ય
    0.78
    變
    0.77
    yout
    0.76
    ing
    0.75
    ̣i
    0.75
    Activations Density 0.000%

    No Known Activations