© 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-262K
    7. 41699
    Prev
    Next
    INDEX
    Explanations

    decisions and ignoring agency

    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_262k_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
     picture
    0.46
     Frau
    0.45
     in
    0.43
    res
    0.42
    rom
    0.42
     '
    0.42
     M
    0.42
     wist
    0.41
     I
    0.41
     L
    0.40
    POSITIVE LOGITS
     decisions
    0.47
     décisions
    0.47
     decisiones
    0.46
     তারা
    0.46
     décide
    0.46
    最后的
    0.45
     κάνει
    0.45
     décider
    0.44
     নির্ধার
    0.44
    papers
    0.43
    Activations Density 0.002%

    No Known Activations