© 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-65K
    7. 40321
    Prev
    Next
    INDEX
    Explanations

    consumers, crime, damage, safety

    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_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
     algae
    0.48
    Active
    0.47
     water
    0.45
    がたくさん
    0.45
     enth
    0.43
    _
    0.43
    Config
    0.43
     ক্যাপ্টেন
    0.42
     पढ़
    0.41
    fully
    0.40
    POSITIVE LOGITS
     consumidores
    0.51
    罪
    0.49
     konsumen
    0.48
     потреби
    0.48
     consommateurs
    0.46
     concealing
    0.45
     criminality
    0.44
     наиболь
    0.44
    安全性
    0.43
     delitos
    0.43
    Activations Density 0.053%

    No Known Activations