© 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-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 1135
    Prev
    Next
    INDEX
    Explanations

    dates and months

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

    month names

    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
    荷重
    0.41
     বিরক্ত
    0.40
     ওয়েবসাইট
    0.40
    ⴻ
    0.40
     በአ
    0.38
     maniac
    0.38
     frameN
    0.38
     vaisseau
    0.38
    <unused106>
    0.38
    TGFuZ
    0.38
    POSITIVE LOGITS
     November
    1.85
     October
    1.84
     September
    1.79
     April
    1.77
     June
    1.75
     December
    1.75
     February
    1.75
     January
    1.71
     August
    1.64
     July
    1.63
    Activations Density 0.201%

    No Known Activations