© 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. 7907
    Prev
    Next
    INDEX
    Explanations

    available, subject to, or awarded

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

    plans and availability

    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
    imbulkan
    0.42
    指摘
    0.40
     ছিলেন
    0.39
     বিজ্ঞানীরা
    0.39
     مجبور
    0.38
    Employ
    0.38
     कुशलता
    0.38
    锷
    0.38
    Capable
    0.38
    masına
    0.37
    POSITIVE LOGITS
     awarded
    1.18
     granted
    1.06
     applicable
    1.02
     berlaku
    0.98
     otorg
    0.96
     valid
    0.96
    granted
    0.93
     redeem
    0.91
     awarding
    0.91
    適用
    0.90
    Activations Density 0.177%

    No Known Activations