Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 3546
    Prev
    Next
    INDEX
    Explanations

    try: input or choice

    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_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
     pandemic
    0.93
     Uttarakhand
    0.85
    ସ
    0.81
     grooming
    0.81
    猢
    0.80
    恂
    0.80
     SARS
    0.79
     zamanda
    0.79
     indices
    0.79
    ༼
    0.79
    POSITIVE LOGITS
     लाश
    0.67
    ''(
    0.66
     amass
    0.66
    mm
    0.64
    imus
    0.64
    incing
    0.63
    Dollar
    0.62
    튜디오
    0.62
    윙
    0.62
    othi
    0.61
    Activations Density 0.043%

    No Known Activations