© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 79660
    Prev
    Next
    INDEX
    Explanations

    danger and negative outcomes

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

    special characters and punctuation

    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_31_width_262k_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
     میشه
    0.57
     çalışan
    0.57
     następnie
    0.56
    优点
    0.54
    镛
    0.54
     yardımcı
    0.54
     müşteri
    0.53
    铖
    0.53
    亼
    0.52
     这是
    0.52
    POSITIVE LOGITS
     perished
    0.55
     risked
    0.53
     threatened
    0.53
     Venezuela
    0.52
     Somalia
    0.51
     calamities
    0.49
     fatalities
    0.47
     緊急
    0.47
     hemorrhagic
    0.47
     около
    0.46
    Activations Density 0.001%

    No Known Activations