© 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. 2334
    Prev
    Next
    INDEX
    Explanations

    to verb infinitive

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

    refuse to be

    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
    น้อง
    0.41
    ​.
    0.41
    '*
    0.39
     '**
    0.39
    ี่
    0.37
     없음
    0.37
    దని
    0.37
     (**
    0.37
    (**
    0.36
    、​
    0.36
    POSITIVE LOGITS
     raised
    0.66
     maneuver
    0.64
     ascertain
    0.62
     Raised
    0.57
    raised
    0.57
     suit
    0.54
    Raised
    0.49
    kyo
    0.46
     attenuate
    0.46
     manoeuvre
    0.46
    Activations Density 0.106%

    No Known Activations