© 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-16K
    7. 2478
    Prev
    Next
    INDEX
    Explanations

    my followed by noun/class

    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_16k_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
     tasmim
    1.37
     shader
    1.29
    📨
    1.28
     middleware
    1.24
     syscall
    1.21
     jika
    1.21
     outfile
    1.20
     xs
    1.19
     subtree
    1.19
     dioxide
    1.18
    POSITIVE LOGITS
    Un
    1.22
    F
    1.22
    S
    1.16
    Ser
    1.15
    Am
    1.11
    J
    1.11
    Re
    1.11
    Und
    1.10
    U
    1.10
    Ch
    1.08
    Activations Density 0.144%

    No Known Activations