© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 45325
    Prev
    Next
    INDEX
    Explanations

    dialogue between

    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_12_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
    ل
    2.27
    nya
    2.20
    ों
    1.99
    ました
    1.89
    ל
    1.77
    ر
    1.76
    د
    1.75
    st
    1.74
    lijke
    1.74
    stores
    1.68
    POSITIVE LOGITS
    ంపు
    1.69
     characterizes
    1.55
     ruffled
    1.50
     এছাড়াও
    1.48
    he
    1.47
     galvanized
    1.47
     sensitized
    1.45
     penalized
    1.42
    ಾಣ
    1.41
     dichloromethane
    1.41
    Activations Density 0.012%

    No Known Activations