© 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. 14963
    Prev
    Next
    INDEX
    Explanations

    numbers and ordinal positions

    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
     ("
    0.71
    டிக்க
    0.71
    군의
    0.68
     (&
    0.67
     [(
    0.67
     ("/
    0.67
     ≈
    0.67
     더
    0.67
    ørende
    0.67
     (“
    0.66
    POSITIVE LOGITS
     ebenfalls
    0.99
     segundo
    0.95
     vijf
    0.93
     terceiro
    0.92
     bottomRight
    0.92
     tercer
    0.90
     grote
    0.90
     zweite
    0.89
     erneut
    0.89
     hiç
    0.87
    Activations Density 0.217%

    No Known Activations