© 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. 16-GEMMASCOPE-2-RES-65K
    7. 207
    Prev
    Next
    INDEX
    Explanations

    death and injury

    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_16_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
    ON
    0.45
    ’
    0.45
    총
    0.45
    ﻘ
    0.45
    출
    0.45
    저는
    0.44
    There
    0.43
    ޯ
    0.43
    ума
    0.42
    ન્સ
    0.42
    POSITIVE LOGITS
     sesuai
    0.44
    ir
    0.44
     injuries
    0.41
     death
    0.40
     thoracique
    0.40
     extrema
    0.39
     setelah
    0.39
     kidneys
    0.39
     gelen
    0.39
     injury
    0.38
    Activations Density 0.264%

    No Known Activations