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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 3335
    Prev
    Next
    INDEX
    Explanations

    long-term, part-time, short-term

    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_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
    د
    1.46
    d
    1.44
    ak
    1.30
    ش
    1.25
    ка
    1.23
    ва
    1.21
    ו
    1.20
    ك
    1.18
    ম
    1.17
    д
    1.16
    POSITIVE LOGITS
    latency
    1.03
     biomed
    0.95
    pecific
    0.93
     prohibitions
    0.91
    ᱼ
    0.91
     renewables
    0.90
     blockchains
    0.89
                
    0.86
                        
    0.86
     crucial
    0.86
    Activations Density 0.048%

    No Known Activations