© 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. 29-GEMMASCOPE-2-RES-262K
    4. 148833
    Prev
    Next
    INDEX
    Explanations

    Tranquility or tranquil

    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_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
     hydride
    0.79
    ρου
    0.77
     والر
    0.75
    雎
    0.75
    selective
    0.72
     réactions
    0.72
     तले
    0.72
    beri
    0.71
    రణ
    0.71
    RV
    0.71
    POSITIVE LOGITS
     Stupid
    0.65
    feito
    0.63
     Fool
    0.62
    缨
    0.61
     Guill
    0.60
     Wrap
    0.60
    Desk
    0.59
    ட்டிய
    0.59
     decreasing
    0.58
     Microphone
    0.58
    Activations Density 0.003%

    No Known Activations