© 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-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 4932
    Prev
    Next
    INDEX
    Explanations

    Large Language Models Explained

    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
     
    0.88
     (
    0.85
     and
    0.83
    ,
    0.78
    ↵
    0.77
     with
    0.76
      
    0.76
     &
    0.75
    .
    0.74
     in
    0.72
    POSITIVE LOGITS
    ChatGPT
    1.19
    TikTok
    1.06
    🥟
    1.01
    Pyrazole
    0.99
     fárm
    0.97
    assaytype
    0.97
    ómago
    0.96
    🥘
    0.96
    🥙
    0.96
    Antaeotricha
    0.95
    Activations Density 0.001%

    No Known Activations