© 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. 1301
    Prev
    Next
    INDEX
    Explanations

    before national, automatic tumor, supervised board

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

    explaining the first point

    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
     Madeline
    0.20
     Ž
    0.19
     Pat
    0.19
     Karen
    0.18
     Aren
    0.18
     Nemours
    0.18
     Menon
    0.18
     María
    0.18
    さんと
    0.18
    ю
    0.17
    POSITIVE LOGITS
    Nc
    0.18
    Qm
    0.18
    ⁉
    0.18
    Bd
    0.18
    。</
    0.18
     wynosi
    0.17
    rtc
    0.17
    RCT
    0.17
     serait
    0.17
     Qc
    0.16
    Activations Density 0.206%

    No Known Activations