© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 36657
    Prev
    Next
    INDEX
    Explanations

    death

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    మ్‌
    0.53
    მოს
    0.50
    ys
    0.46
     ፓ
    0.45
     ልዩ
    0.45
    젠
    0.44
     optimised
    0.44
    ক্লা
    0.44
    MO
    0.43
    ีน
    0.43
    POSITIVE LOGITS
     death
    1.49
     Death
    1.38
    death
    1.33
     muerte
    1.31
    Death
    1.28
     DEATH
    1.15
     morte
    1.13
    死
    1.06
     مرگ
    1.05
    死亡
    1.04
    Activations Density 0.060%

    No Known Activations