© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 7459
    Prev
    Next
    INDEX
    Explanations

    handling multiple items together

    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
     itself
    1.58
     its
    1.53
     Its
    1.34
    了一个
    1.27
     такой
    1.25
     яке
    1.23
    e
    1.20
     самое
    1.18
     Такая
    1.18
     delgado
    1.18
    POSITIVE LOGITS
    atically
    2.53
     جميعا
    2.15
     كلهم
    2.07
    م
    1.80
     fleste
    1.69
    各自
    1.67
    mselves
    1.66
     jeweiligen
    1.65
    ों
    1.64
     themselves
    1.64
    Activations Density 0.065%

    No Known Activations