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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 4922
    Prev
    Next
    INDEX
    Explanations

    modern everyday concepts

    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_65k_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
    ెల
    0.67
    
    0.65
    ิ่น
    0.65
    izm
    0.64
    idders
    0.63
    Ꮔ
    0.62
    র্ব
    0.61
    надцати
    0.60
    ocarpus
    0.60
    <unused9>
    0.60
    POSITIVE LOGITS
     modern
    4.02
     nowadays
    3.80
     today
    3.74
     Nowadays
    3.53
     moderno
    3.51
    modern
    3.42
    Nowadays
    3.42
     moderne
    3.41
     современных
    3.41
     современные
    3.38
    Activations Density 1.941%

    No Known Activations