© 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. 2679
    Prev
    Next
    INDEX
    Explanations

    rules of thumb

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

    rough estimates and guidelines

    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
    キュ
    0.42
     गुंतवण
    0.39
     ダウン
    0.39
    inerary
    0.39
     सामूहिक
    0.38
     沒有
    0.38
     帽
    0.38
     購入
    0.38
     Veranstaltung
    0.38
     Ичиго
    0.37
    POSITIVE LOGITS
     approximate
    0.71
     approximation
    0.64
     doubling
    0.63
     Approximate
    0.62
    approx
    0.59
    Approx
    0.59
    近似
    0.59
     approxim
    0.58
     approximations
    0.57
     approximated
    0.55
    Activations Density 0.000%

    No Known Activations