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

    Neuronpedia

    Jacobian LensNEW
    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. 13455
    Prev
    Next
    INDEX
    Explanations

    in, at, and related phrases

    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
    longitude
    0.87
    ുകയായിരുന്നു
    0.81
    ilustración
    0.81
     ترین
    0.79
    WithOwner
    0.79
    sentation
    0.77
    ௐ
    0.75
    linear
    0.74
    ﻄ
    0.74
    édition
    0.73
    POSITIVE LOGITS
     existence
    0.93
     involved
    0.88
     hand
    0.86
     vorhanden
    0.85
     наличии
    0.83
     disponível
    0.82
     handy
    0.79
     ready
    0.79
     मौजूद
    0.78
    存在
    0.78
    Activations Density 0.058%

    No Known Activations