© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 12157
    Prev
    Next
    INDEX
    Explanations

    purpose or target

    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
     вам
    1.40
     вас
    1.35
    你的
    1.31
     你
    1.30
     Bạn
    1.26
    あなた
    1.25
    Your
    1.22
     тебе
    1.22
    You
    1.21
     вашей
    1.21
    POSITIVE LOGITS
     bagi
    1.96
     لدى
    1.32
     بالنسبة
    1.15
     Bagi
    1.11
     for
    1.05
    让
    1.03
     encourages
    1.02
     encourage
    1.01
    สำหรับ
    1.00
    bagi
    0.99
    Activations Density 0.193%

    No Known Activations