© 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. 2015
    Prev
    Next
    INDEX
    Explanations

    dates and ordinals

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

    day number 21

    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
     Trink
    0.41
    渎
    0.40
     fēng
    0.39
    𒋢
    0.38
     shade
    0.38
    ஷம்
    0.38
     ٻ
    0.36
    دوس
    0.36
     अवसरों
    0.36
     aparência
    0.36
    POSITIVE LOGITS
    th
    1.05
    rd
    0.71
     ቀን
    0.68
    <sup>
    0.67
    nd
    0.67
    st
    0.64
     তারিখে
    0.63
    ths
    0.57
    thand
    0.57
     deadline
    0.56
    Activations Density 0.233%

    No Known Activations