© 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
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3254
    Prev
    Next
    INDEX
    Explanations

    years followed by a parenthesis

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

    year followed by punctuation

    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
    डिया
    0.47
    িনের
    0.44
    ाइंड
    0.44
    ଷ
    0.43
    ूल
    0.41
    ্্র
    0.41
     yet
    0.40
    मस
    0.39
    ClrBit
    0.39
     headaches
    0.38
    POSITIVE LOGITS
    年
    1.23
    년
    1.16
     yılında
    1.04
    년부터
    1.04
    年から
    0.97
    年的
    0.96
    년에
    0.95
     সালের
    0.93
    年在
    0.89
    年モデル
    0.88
    Activations Density 0.153%

    No Known Activations