© 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. 2655
    Prev
    Next
    INDEX
    Explanations

    transformer architecture, SSD, Wi, shiny Pokémon

    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
    siniz
    3.16
    signUp
    3.05
    ниях
    3.03
     ellipses
    3.01
    
    3.00
    न
    2.97
    soever
    2.85
    nama
    2.84
    ⎛
    2.80
    тесь
    2.79
    POSITIVE LOGITS
    ہ
    3.37
    ์
    3.26
    ☜
    3.22
    儿
    3.06
    𝘂
    2.97
    𝘆
    2.94
    𝗹
    2.84
    𝗱
    2.76
    兒
    2.75
     pukul
    2.73
    Activations Density 0.437%

    No Known Activations