© 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. 2293
    Prev
    Next
    INDEX
    Explanations

    output formatting

    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
    terus
    0.67
     считают
    0.64
    骄
    0.63
    딜
    0.62
    चय
    0.61
     overruling
    0.60
    噪
    0.60
    庝
    0.58
    চ্ছেদ
    0.58
    ટી
    0.57
    POSITIVE LOGITS
     format
    2.86
     formato
    2.76
     form
    2.73
    形式
    2.72
    的形式
    2.70
     formats
    2.68
     формата
    2.62
     forme
    2.52
     Format
    2.51
     forma
    2.51
    Activations Density 0.458%

    No Known Activations