© 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-65K
    7. 6579
    Prev
    Next
    INDEX
    Explanations

    file paths and function calls

    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
     cuadrado
    0.82
     சது
    0.77
    Tim
    0.77
     Boul
    0.74
    Year
    0.73
     лице
    0.71
    Buildings
    0.71
    痫
    0.69
    Crack
    0.68
     quadrado
    0.68
    POSITIVE LOGITS
     erity
    0.76
    ージー
    0.76
     particular
    0.72
     thân
    0.71
    нут
    0.69
    仑
    0.64
    iyat
    0.64
    으니까
    0.64
    nements
    0.64
     frowned
    0.62
    Activations Density 0.001%

    No Known Activations