© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2625
    Prev
    Next
    INDEX
    Explanations

    birds, heart, Tweet, robin

    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_9_width_16k_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
     allusion
    3.00
    ف
    2.81
    ક
    2.80
    ک
    2.75
    𝒕
    2.70
    ad
    2.68
    ziger
    2.65
    ಾ
    2.62
    তান্ত্রিক
    2.58
    𝒂
    2.57
    POSITIVE LOGITS
    ㅌ
    3.35
    "\
    3.13
    其他
    3.12
    clientX
    3.07
    spiration
    2.97
    pageY
    2.85
     numberOf
    2.77
     potom
    2.76
    فاوت
    2.74
    न
    2.71
    Activations Density 0.279%

    No Known Activations