© 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
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 5720
    Prev
    Next
    INDEX
    Explanations

    # markers and delimiters

    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
    Street
    0.65
    Income
    0.59
    Survival
    0.59
    <unused301>
    0.59
    Wars
    0.58
    Monitoring
    0.58
    Baby
    0.57
    Celebrating
    0.57
    Drug
    0.57
    Ali
    0.57
    POSITIVE LOGITS
    ும்
    0.66
     nuance
    0.61
    は見
    0.60
     ठ
    0.58
    ものを
    0.57
     style
    0.56
     يح
    0.55
     embeddings
    0.55
     ৩
    0.54
     pit
    0.54
    Activations Density 0.051%

    No Known Activations