© 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. 25284
    Prev
    Next
    INDEX
    Explanations

    overly glamorous

    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
    ט
    0.53
    لون
    0.48
    х
    0.46
    还能
    0.46
    煅
    0.46
    т
    0.46
     असलेले
    0.46
    י
    0.45
    监控
    0.45
    伦
    0.45
    POSITIVE LOGITS
     yoki
    0.45
    set
    0.44
     preparar
    0.44
     подготовке
    0.43
     substit
    0.43
     preparing
    0.43
        
    0.42
     подгото
    0.42
     idiosyncratic
    0.41
     choirs
    0.41
    Activations Density 0.003%

    No Known Activations