© 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. 14731
    Prev
    Next
    INDEX
    Explanations

    Keywords:

    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
    名
    0.67
    을
    0.62
    명을
    0.61
     説明
    0.60
    명
    0.60
     प्रयास
    0.60
     wouldn
    0.59
     imparting
    0.59
     doing
    0.59
    ազմ
    0.58
    POSITIVE LOGITS
     genética
    0.90
    Mad
    0.86
    ❙
    0.86
    Scenic
    0.83
    мед
    0.83
    क्की
    0.83
    antib
    0.83
    Stage
    0.83
    ◼
    0.82
    loven
    0.81
    Activations Density 0.000%

    No Known Activations