© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 14305
    Prev
    Next
    INDEX
    Explanations

    numbers 2 and 3

    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_22_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
    ↵
    0.87
     Babylon
    0.54
     flashed
    0.52
    arr
    0.52
    霹
    0.52
    ira
    0.52
    olor
    0.52
    taire
    0.52
    odian
    0.51
    ss
    0.51
    POSITIVE LOGITS
     üretim
    0.94
    
    0.91
     პროფილი
    0.87
     sfrutt
    0.85
    倛
    0.85
    Ⴀ
    0.82
    醿
    0.81
     produção
    0.81
     चार
    0.81
     உட
    0.79
    Activations Density 0.009%

    No Known Activations