© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12326
    Prev
    Next
    INDEX
    Explanations

    skilled labor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵↵
    2.60
    ↵↵↵↵↵↵↵
    2.41
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    2.39
    ↵↵↵↵↵
    2.32
    ↵↵↵↵↵↵↵↵↵↵↵
    2.28
    ↵↵↵↵
    2.26
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    2.24
    ↵↵↵↵↵↵
    2.24
     걸
    2.18
    گاہ
    2.18
    POSITIVE LOGITS
    𝑢
    2.77
    uacute
    2.66
    𝗨
    2.59
     ascend
    2.57
    𝙡
    2.56
    entuan
    2.53
    Comparator
    2.52
    𝙣
    2.48
    UserRepository
    2.47
    ◼
    2.44
    Activations Density 0.032%

    No Known Activations