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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 2731
    Prev
    Next
    INDEX
    Explanations

    than, learned, less, of

    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
     teman
    1.14
    ر
    1.14
    eleg
    1.12
    e
    1.10
     மற
    1.10
    xing
    0.97
    ゴルフ
    0.96
    {|\
    0.96
     дей
    0.94
     liya
    0.94
    POSITIVE LOGITS
    ensão
    1.05
     governo
    1.05
     insuficiente
    1.02
    assurance
    1.01
     saudável
    1.01
    akal
    0.98
    setNome
    0.96
    ათ
    0.96
    ificação
    0.96
     durchaus
    0.95
    Activations Density 0.000%

    No Known Activations