© 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. 19084
    Prev
    Next
    INDEX
    Explanations

    playback controls and state

    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
    Cogn
    0.89
    Morgan
    0.89
    Moody
    0.79
    Austin
    0.74
    具
    0.74
    adays
    0.74
     মনো
    0.72
    可以使用
    0.71
    Louisiana
    0.71
    aceous
    0.71
    POSITIVE LOGITS
     halted
    0.91
     Failed
    0.90
     []*
    0.88
     failed
    0.87
     Moved
    0.86
     halve
    0.84
     stali
    0.83
     refrained
    0.80
     evitare
    0.80
     paused
    0.80
    Activations Density 0.001%

    No Known Activations