© 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
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5088
    Prev
    Next
    INDEX
    Explanations

    millions of

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

    millions or billions of

    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
     billion
    0.56
     thousand
    0.54
    thousand
    0.53
    billion
    0.50
    萬
    0.47
    万人
    0.47
     trillion
    0.47
    Thousands
    0.47
    thousands
    0.46
     हजारों
    0.45
    POSITIVE LOGITS
    uzie
    0.39
    苳
    0.37
     suffer
    0.37
     apprend
    0.37
    qst
    0.37
     rely
    0.36
    께서
    0.36
     helped
    0.36
    ীব্র
    0.36
     تتح
    0.36
    Activations Density 0.000%

    No Known Activations