© 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-16K
    7. 1462
    Prev
    Next
    INDEX
    Explanations

    end of list

    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
     (“
    1.21
     (
    1.10
     ("
    1.09
     („
    0.87
    (
    0.86
     "
    0.83
    :
    0.82
    🔥🔥
    0.81
    /"
    0.81
     “
    0.81
    POSITIVE LOGITS
    倘
    1.17
    瞧
    1.08
     delectable
    1.07
    Surely
    1.04
    或许
    1.03
    きっと
    0.98
     تلك
    0.97
     ought
    0.96
     divulge
    0.96
     soltanto
    0.95
    Activations Density 0.589%

    No Known Activations