© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11728
    Prev
    Next
    INDEX
    Explanations

    lack of engagement, indifference

    np_acts-logits-general · gemini-2.5-flash-lite

    lack of warmth or enthusiasm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    贊
    0.44
    एक्स
    0.43
    वय
    0.43
    เหมาะสม
    0.42
    肨
    0.42
    ORD
    0.41
    พลาด
    0.41
    NAB
    0.41
    玻
    0.41
    欢乐
    0.41
    POSITIVE LOGITS
     indifference
    1.43
     indifer
    1.30
     indifferent
    1.27
     coldly
    1.13
     aloof
    1.09
     apathy
    1.01
     refusal
    0.99
     disdain
    0.97
     nonchal
    0.97
     उदासीन
    0.94
    Activations Density 0.089%

    No Known Activations