© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 4643
    Prev
    Next
    INDEX
    Explanations

    `Event` or `you`

    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_262k_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
    allenges
    1.47
     AudioClip
    1.35
    androidx
    1.33
    ComponentScan
    1.31
    दात
    1.28
     Agreements
    1.26
    않
    1.26
    o
    1.23
     EditText
    1.23
    genes
    1.21
    POSITIVE LOGITS
    ко
    1.04
     hebat
    1.00
    ाइ
    0.94
     largement
    0.94
     impressive
    0.90
    وك
    0.89
    ка
    0.88
     tahu
    0.87
     delightfully
    0.87
    টা
    0.86
    Activations Density 0.002%

    No Known Activations