© 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-262K
    7. 12494
    Prev
    Next
    INDEX
    Explanations

    synthetic or startup examples

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    aan
    1.99
    oğlu
    1.84
    t
    1.82
    ي
    1.75
    берите
    1.74
    iune
    1.73
     uygun
    1.69
    ضي
    1.65
    dı
    1.64
    ০
    1.64
    POSITIVE LOGITS
    وں
    1.98
    ها
    1.97
     guesses
    1.88
    ist
    1.84
    おそらく
    1.79
    ‌ها
    1.79
    ता
    1.76
     underestimates
    1.74
    СТЬ
    1.72
    ﻪ
    1.71
    Activations Density 0.029%

    No Known Activations