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. 29-GEMMASCOPE-2-RES-65K
    4. 1822
    Prev
    Next
    INDEX
    Explanations

    honest, candid observations

    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_29_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
     كما
    0.81
    อย่างไร
    0.77
    अभिने
    0.76
     نشان
    0.76
     удовольствием
    0.76
    
    0.75
     것으로
    0.74
     باشد
    0.73
     действи
    0.73
     것이
    0.71
    POSITIVE LOGITS
     lmao
    1.85
     idk
    1.68
     tbh
    1.66
     vibes
    1.45
    💀
    1.36
     legit
    1.36
     fucking
    1.34
     dude
    1.33
     fuck
    1.30
     kinda
    1.28
    Activations Density 0.593%

    No Known Activations