© 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. 1919
    Prev
    Next
    INDEX
    Explanations

    punctuation at end of text

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

    and so on

    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
     angiogenic
    0.20
    মিক্যাল
    0.20
     belted
    0.19
    র্কের
    0.19
    टकों
    0.19
    ֖
    0.19
    нодоро
    0.19
     acetaminophen
    0.19
     теркәлү
    0.18
     Rồi
    0.18
    POSITIVE LOGITS
    ↵↵↵
    0.23
    ↵↵↵↵
    0.23
    以及
    0.22
    ↵↵↵↵↵
    0.22
    ↵↵↵↵↵↵
    0.21
     bref
    0.21
    ↵↵↵↵↵↵↵↵↵↵↵
    0.21
    who
    0.21
    ↵↵↵↵↵↵↵
    0.21
    いや
    0.21
    Activations Density 0.004%

    No Known Activations