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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 14933
    Prev
    Next
    INDEX
    Explanations

    personal choice

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     th
    0.58
    的作用
    0.57
    ^(-
    0.56
     चुनौ
    0.55
     forbidden
    0.54
     നേടിയ
    0.53
     impact
    0.53
    节能
    0.52
    窝
    0.52
    ^(
    0.51
    POSITIVE LOGITS
     discretion
    1.74
     convenience
    1.36
     liking
    1.23
     whim
    1.16
     pleasure
    1.14
     discre
    1.11
     prerogative
    1.05
     volition
    1.04
     Convenience
    1.01
     discernment
    1.01
    Activations Density 0.098%

    No Known Activations