© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15825
    Prev
    Next
    INDEX
    Explanations

    conditional statements or reasoning

    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
    }\,\
    0.75
     chill
    0.71
     situation
    0.69
     ambitions
    0.67
     pinch
    0.66
     Teflon
    0.66
     Transformations
    0.64
     Benin
    0.64
    祸
    0.62
     synagogue
    0.62
    POSITIVE LOGITS
    ="'$(
    1.00
    naires
    0.93
    nement
    0.92
    COND
    0.86
    条件
    0.82
     条件
    0.82
    stopwords
    0.81
    ning
    0.80
    조건
    0.79
    ality
    0.78
    Activations Density 0.124%

    No Known Activations