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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 5287
    Prev
    Next
    INDEX
    Explanations

    numbers and multiple languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     限定
    0.89
     इनोवेशन
    0.84
     Ausdruck
    0.82
     昨日
    0.80
     调用
    0.80
     효과
    0.80
    㩴
    0.80
     成分
    0.78
     行っ
    0.77
     वीडियोस
    0.76
    POSITIVE LOGITS
    ↵↵
    0.92
    también
    0.86
    ↵
    0.80
    because
    0.77
    2
    0.74
    
    0.71
     ponieważ
    0.71
     perché
    0.71
    you
    0.70
     funcionários
    0.70
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.