© 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-3-12B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 3327
    Prev
    Next
    INDEX
    Explanations

    disclaimer: I am an AI chatbot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_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
    limit
    0.77
    ,
    0.77
     warning
    0.71
     error
    0.70
     in
    0.69
     simplified
    0.68
    modify
    0.67
     caution
    0.67
     corrected
    0.66
    :
    0.66
    POSITIVE LOGITS
     Everyone
    1.19
     Każ
    1.16
     Seorang
    1.12
     Studies
    1.11
     Anyone
    1.11
     Every
    1.09
     Requirements
    1.09
     There
    1.07
     Different
    1.07
     Managing
    1.06
    Activations Density 0.033%

    No Known Activations