© 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-16K
    7. 7664
    Prev
    Next
    INDEX
    Explanations

    stack operations

    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
     चाइ
    0.63
     snail
    0.63
     fertilizer
    0.63
     whiskers
    0.62
     Celsius
    0.61
     disseminated
    0.61
    涂
    0.61
    awasan
    0.61
     getroffen
    0.60
     vegetable
    0.60
    POSITIVE LOGITS
     stack
    1.42
    Stack
    1.40
     Stack
    1.32
    栈
    1.23
    Stacked
    1.23
    stack
    1.21
     stacks
    1.20
     navigation
    1.17
     stacking
    1.17
    Navigation
    1.14
    Activations Density 0.153%

    No Known Activations