© 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. 41-GEMMASCOPE-2-RES-65K
    7. 1404
    Prev
    Next
    INDEX
    Explanations

    action or state

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_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
     đều
    0.53
    都能
    0.50
     ہیں۔
    0.48
    >
    0.47
    人都
    0.44
    都知道
    0.43
     имели
    0.42
    之类的
    0.42
    都
    0.42
     lainnya
    0.41
    POSITIVE LOGITS
     originates
    0.79
     distinguishes
    0.76
     aligns
    0.76
    inerary
    0.76
     seeks
    0.75
     encompasses
    0.75
     exists
    0.74
     calculates
    0.74
     generates
    0.73
     utilizes
    0.73
    Activations Density 0.407%

    No Known Activations