© 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. 2324
    Prev
    Next
    INDEX
    Explanations

    explaining definitions or properties

    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
     which
    0.60
     thereof
    0.59
    .[
    0.54
    .”
    0.52
    ."""
    0.51
     которого
    0.49
     or
    0.49
    [
    0.49
    which
    0.49
     thereon
    0.48
    POSITIVE LOGITS
     prides
    1.05
     selalu
    0.93
     memiliki
    0.90
     bekerja
    0.90
     সাধারণত
    0.87
     belongs
    0.86
     mempunyai
    0.85
     dikenal
    0.84
     inherently
    0.84
     pertenece
    0.82
    Activations Density 0.285%

    No Known Activations