© 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
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 10647
    Prev
    Next
    INDEX
    Explanations

    skill level

    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_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
    鮮
    0.69
     Sonne
    0.69
    കം
    0.69
     passionate
    0.66
    ikalische
    0.66
    ánico
    0.63
     mắn
    0.63
     tradición
    0.62
     Vorsch
    0.61
    剱
    0.61
    POSITIVE LOGITS
     level
    4.33
    level
    3.99
    Level
    3.77
    レベル
    3.67
     niveau
    3.66
     Level
    3.63
     nivel
    3.58
     nível
    3.47
     livello
    3.46
     levels
    3.45
    Activations Density 0.478%

    No Known Activations