Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7359
    Prev
    Next
    INDEX
    Explanations

    reducing negative outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    ين
    1.89
    नों
    1.84
    𝘳
    1.79
    \$
    1.77
    𝘮
    1.71
    রাও
    1.70
    𝘺
    1.70
     والمع
    1.64
    𝘵
    1.64
    र
    1.57
    POSITIVE LOGITS
     $(<
    2.05
     thiểu
    1.79
     charla
    1.67
    ↓↓
    1.61
    ्युनिटी
    1.57
    àu
    1.51
     совсем
    1.51
    
    1.51
     thiệu
    1.50
    Proposition
    1.49
    Activations Density 0.264%

    No Known Activations