© 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. 30116
    Prev
    Next
    INDEX
    Explanations

    military branches, storing sensitive information

    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
    <code>
    0.45
    带来的
    0.44
    增加
    0.44
    帶來
    0.43
    discord
    0.42
    捣
    0.42
    Discord
    0.41
    实现
    0.40
    如果
    0.40
    🤞
    0.40
    POSITIVE LOGITS
     jurisprudence
    0.50
     journaliste
    0.45
    രുന്നു
    0.44
     syll
    0.42
     énorm
    0.42
     literat
    0.42
     літера
    0.41
     în
    0.41
     ਤੁਸੀਂ
    0.41
     semula
    0.40
    Activations Density 0.008%

    No Known Activations