© 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. 17490
    Prev
    Next
    INDEX
    Explanations

    Deputy Attorney, Power of Attorney

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

    Atatürk, At, ATH, atrium

    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
    谏
    0.41
    HeaderAccept
    0.40
    erecht
    0.40
    塙
    0.39
    卜
    0.38
     ይቀ
    0.38
    aneamente
    0.37
     腰
    0.36
    ujudkan
    0.35
    訸
    0.35
    POSITIVE LOGITS
     ат
    3.22
     Ат
    3.08
     AT
    2.84
     Atkinson
    2.66
     Atkins
    2.63
     ATLAS
    2.63
     ATF
    2.63
    <0x81>
    2.61
     ATR
    2.61
     Ath
    2.59
    Activations Density 0.343%

    No Known Activations