© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 229757
    Prev
    Next
    INDEX
    Explanations

    ; Volume, (v)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    bled
    0.45
     ayer
    0.44
    ادي
    0.44
    ired
    0.44
    ائدة
    0.43
    بر
    0.42
    all
    0.41
    ذ
    0.41
    penas
    0.40
     hydraulics
    0.39
    POSITIVE LOGITS
     सरस्व
    0.50
     lɛ
    0.44
     பல்கலை
    0.41
    आईए
    0.41
    📫
    0.41
     جدید
    0.40
     および
    0.40
     Tunisie
    0.39
     জাতিসঙ্ঘ
    0.39
     کاکروچ
    0.39
    Activations Density 0.000%

    No Known Activations