© 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. 24-GEMMASCOPE-2-RES-16K
    4. 6698
    Prev
    Next
    INDEX
    Explanations

    color and scrollbar styles

    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
    
    0.93
     (“
    0.89
     Continuing
    0.86
     Centuries
    0.82
    
    0.82
     Communism
    0.79
     Circum
    0.78
     Computational
    0.77
    Bankruptcy
    0.75
     Admit
    0.75
    POSITIVE LOGITS
    ol
    0.84
    ojen
    0.82
    ר
    0.80
    q
    0.77
    ar
    0.76
    你们
    0.75
     Jako
    0.75
    나
    0.75
    카
    0.74
    야
    0.74
    Activations Density 0.001%

    No Known Activations