© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 2413
    Prev
    Next
    INDEX
    Explanations

    loss of babies

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

    affectionate closings

    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_53_width_65k_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
     excitation
    0.49
     நிர்
    0.45
    excitation
    0.45
     उत्साहित
    0.43
     alakalı
    0.42
     만족
    0.41
    咦
    0.41
     মোটামুটি
    0.41
     memnun
    0.40
     заинтере
    0.40
    POSITIVE LOGITS
     sorrow
    1.11
    💔
    1.05
     condolences
    0.99
     grieving
    0.99
     grief
    0.96
     grieve
    0.96
     Prayers
    0.96
     prayers
    0.95
     condol
    0.94
     mourn
    0.93
    Activations Density 0.216%

    No Known Activations