© 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. 2659
    Prev
    Next
    INDEX
    Explanations

    to the

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

    to [noun/phrase]

    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
    .
    0.40
     toget
    0.38
     (!)
    0.38
     Including
    0.37
     THEY
    0.36
     från
    0.35
     propre
    0.34
     inklusive
    0.34
    s
    0.34
     AGAIN
    0.34
    POSITIVE LOGITS
     ensure
    0.83
     accommodate
    0.78
     illustrate
    0.78
     alleviate
    0.77
     facilitate
    0.77
     appease
    0.75
     be
    0.71
     encourage
    0.71
     achieve
    0.71
     enhance
    0.71
    Activations Density 0.672%

    No Known Activations