© 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. 29-GEMMASCOPE-2-RES-16K
    7. 888
    Prev
    Next
    INDEX
    Explanations

    on steroids

    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_29_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
    s
    0.80
    Error
    0.77
    传输
    0.73
    eyed
    0.73
    abcd
    0.72
    oretical
    0.71
    য়াল
    0.71
    ς
    0.70
    assertEquals
    0.70
    ামের
    0.69
    POSITIVE LOGITS
     behalf
    2.76
     top
    1.98
     occasion
    1.82
     steroids
    1.68
    top
    1.65
     horseback
    1.62
     demand
    1.53
    demand
    1.52
    Demand
    1.46
     Demand
    1.43
    Activations Density 0.311%

    No Known Activations