© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 148
    Prev
    Next
    INDEX
    Explanations

    vibrant colors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
    Cups
    0.62
    er
    0.61
     nhàng
    0.61
    髅
    0.60
    嵓
    0.59
     rested
    0.59
    s
    0.59
     marital
    0.59
    cognitive
    0.58
    抂
    0.58
    POSITIVE LOGITS
    径
    0.78
     Transparency
    0.74
     باید
    0.71
    持續
    0.71
    繼續
    0.70
     drainage
    0.70
     beper
    0.70
     pesado
    0.69
     و
    0.69
    adz
    0.69
    Activations Density 0.021%

    No Known Activations