© 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-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 4859
    Prev
    Next
    INDEX
    Explanations

    card numbers

    np_acts-logits-general · gemini-2.5-flash-lite

    numbers and symbols in lists or sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_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
    ынша
    0.41
     sejahtera
    0.38
    uento
    0.38
     மருத்து
    0.38
    ⃞
    0.38
     mayores
    0.36
     जुट
    0.36
    勃
    0.35
    ╴
    0.35
     गर
    0.35
    POSITIVE LOGITS
    рэ
    0.40
    q
    0.40
    غل
    0.38
    க்கம்
    0.36
    phal
    0.36
    構
    0.36
     мень
    0.35
    сці
    0.34
     Frem
    0.34
    alya
    0.33
    Activations Density 0.210%

    No Known Activations